Low Detection Efficiency Research Articles

An Oil Multipollutant Detection Sensor With High Sensitivity and High Throughput

Oil is rich in information about the operating status of machinery and equipment, and oil condition monitoring is essential for maintaining the safety and reliability of machinery and equipment. Most sensors not only have the problem of small detection throughput and low detection efficiency, but also large-sized contaminants can easily block or even scratch the detection channel. A sensor with high sensitivity and high throughput for detecting multiple oil contamination is designed in this paper. The sensor comprises four glass capillary detection channels and four detection units, including a planar coil, solenoid coil, cylindrical parallel plate capacitor and rectangular parallel plate capacitor. Detection flux of the sensor is increased by 12 times its initial value, which significantly improves the detection efficiency. Through experimental research, in the inductance mode, the best excitation frequency is 2 MHz, and the voltage is 2 V. In the capacitance mode, the best excitation frequency is 1.8 MHz, and the voltage is 2 V. In addition, the sensor has a higher detection capability for Fe than Cu in the inductance mode, and a higher detection capability for water droplets than air bubbles in the capacitance mode. By analyzing the signal characteristics of each sensor unit, the sensor can distinguish between Fe of 38~900 μm and Cu of 88~900 μm, as well as water droplets greater than 130 μm and air bubbles greater than 100 μm. This research provides a new idea for online oil monitoring.

Efficient Recognition of Facial Expression with Lightweight Octave Convolutional Neural Network

In various social activities, people usually focus on the other person’s facial expression, which is an important element in interpersonal communication. The facial expression typically reflects a person’s current mood and conveys emotional information. Perceiving the facial expressions of people in images through cameras has always been a popular research topic. Previous studies have classified facial expressions into different categories, such as happy, sad, fear, angry, calm, disgust and surprise, and have identified them using image processing methods. However, traditional image processing methods have a low detection efficiency and low recognition accuracy due to variation of perspectives. As a result, most of them can only be applied to the front face and short distance situations. In this paper, we propose a lightweight deep learning framework for facial expression recognition using Octave convolutional neural network (FerOctNet). FerOctNet including multi-scale convolutional processing and residual learning is able to obtain multi-scale features with enriched representation ability by integrating the deep level features with rich semantic information with shallow details of the features. Compared with other deep learning networks, not only does the proposed method have a good recognition rate, but also contains fewer parameters in the network.

Research on Improved Residual Network Classification Method for Defect Recognition of Thermal Battery

Thermal battery is an ideal power supply for military applications such as artillery and ship equipment. Due to the sheet-type process of the thermal battery, various installation error defects occur in the assembly of thermal battery. Aiming at the problems of low efficiency and low defect-recognition rate of thermal battery detection, a thermal battery defect detection model is proposed based on residual network. First, the squeeze-and-excitation networks (SENet) structure based on the attention mechanism is introduced into residual block of the residual neural network, the connection between the feature extraction channels is established, and the improved deep residual network I-ResNet50 is obtained; Second, in order to prevent overfitting, the defect images processed in the production line and the laboratory are data-enhanced and labeled. Transfer learning strategy is introduced into the recognition model I-ResNet50, and then the training set data samples are input into the recognition model I-ResNet50 for training, and the activation function LReLu and Dropout skills are introduced to improve the classification ability of the I-ResNet50 model; Finally, the recognition model I-ResNet50 is applied to the test set and validation set, and each defect of the thermal battery are output. Comparison experiments are tested under different migration strategies and different optimizers and learning rates, and comparison experiments with the five classic network structures of ResNet50, YOLOV3, MobileNetV2, VGG16, and YOLOV4 are also tested. The test data show that the recognition accuracy rates of qualified images and the three types of defective images (Qualified Assembly, Missing Current Plate, Wrong Number of Stacks, and Reverse Stack) can reach 99.64%, 98.17%, 99.11%, and 95.40%, respectively, the overall recognition accuracy rate can reach 98.10%. The test results illustrate the model can detect thermal battery defects more accurately and quickly, and has good defect diagnosis ability, which is nearly 5% higher than the traditional method, and a new solution for defect detection in practical industrial scenarios of thermal battery is provided.

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

In the process of production, automobile steel forgings are prone to various cracks, which affect the product quality. At present, forgings defects are mainly detected by fluorescent magnetic particle inspection and manual inspection. Aiming at the problems of low detection accuracy and efficiency in this method, an improved convolutional neural network model is proposed. The fluorescent magnetic particle inspection images of two typical forgings were intelligently inspected. Firstly, a deep learning model with EfficientNet as the backbone and Feature Pyramid Network (FPN) as the fusion layer is constructed. Secondly, In order to improve the convergence speed and detection accuracy, the calculation method of intersection over union is improved, and the network is improved by using the Attention Mechanism. Finally, Particle Swarm Optimization algorithm (PSO) with adaptive parameters is introduced to optimize the hyperparameters of neural network, and a fluorescent magnetic particle inspection image acquisition platform is built for verification. The mean Average Precision (mAP) of the best model of EfficientNet-PSO on the validation set is 95.69%. F1 score is 0.94 and FLOPs is 1.86B. Compared with other five deep learning neural network models, this method effectively improves the defect detection efficiency and accuracy of flange plate and cylinder head, which can meet the defect detection requirements.

Measurement and Analysis of Soil Temperature Field Based on Fiber Bragg Grating Sensor Array

Studying the soil temperature field and its variation law is of great significance to the real-time service of agricultural production. To solve the problems of low detection efficiency and difficulty of distributed detection, a distributed detection method of soil temperature field using wavelength division multiplexing and space division multiplexing technologies based on fiber Bragg grating (FBG) sensor is proposed. In this scheme, the stainless steel tube encapsulating the FBG string was vertically buried in the measured soil, and the tunable laser method and the peak-seeking algorithm were used to demodulate the wavelength of each sensor of the FBG string. The soil temperature field measurement experiments were carried out in the farmland environment. The experimental results show that the proposed method can detect the soil temperature field in real time. The internal temperature of soil changes periodically with the periodic change of surface environment temperature. With the increase of depth, the influence of surface temperature on soil temperature gradually decreases, and the amplitude of soil temperature oscillation gradually decreases, but the hysteresis effect of temperature peak becomes more and more obvious. The ambient wind speed can reduce the temperature of soil surface and shallow layer. Soil moisture affects the speed of temperature transfer from the surface layer to the deep layers, and the hysteresis effect of temperature peak is more significant in the soil with higher moisture. Solar radiation has a great influence on the temperature of soil surface and shallow layer.

Realization of Multi-Frequency Resonance for a Portable Near-Surface Frequency-Domain Electromagnetic Transmitting System

Portable near-surface frequency-domain electromagnetic (FDEM) instruments are effective tools for detecting underground electrical abnormal targets. However, due to the inductive reactance of the transmitting coil, conventional instruments cannot transmit high amplitude current at multiple frequencies at the same time in the high frequency range (>1000 Hz). This would lead to low detection efficiency and poor signal-to-noise ratio of the system and would ultimately affect the detection accuracy. In view of the above problems, a multi-frequency resonant strategy is proposed to simultaneously increase the transmitting current amplitude at multiple target frequencies. First, the multi-frequency resonance theory is analyzed and the circuit parameter solving method is improved. The validity of the multi-frequency resonance theory and the solution method is verified via circuit simulation. Further, the influence of the component parameter deviation on the circuit resonance is analyzed, and the selection principle of the resonance parameters based on the quality factor Q is presented. Considering the actual deviation, a five-frequency or seven-frequency resonant circuit may achieve a better resonance effect than the nine-frequency resonant circuit in practice. Finally, the strategy is validated with an actual circuit. The results show that the constructed five-frequency resonant circuit can effectively increase the amplitude at the target frequency. The maximum increase is 10.50 times, and the transmitting energy is 11.4 times higher. This study provides a feasible implementation method for multi-frequency resonance at five frequencies and above, which is helpful for improving the detection efficiency and signal-to-noise ratio of a portable near-surface FDEM system.

A study on depth classification of defects by machine learning based on hyper-parameter search

To overcome the low efficiency of crack depth detection of steel, we explored for the first time the method based on hyper-parameters search in the field of defect depth classification. And the effect of different defect depths on the heat transfer to the metal surface during heating and cooling process was analyzed. Moreover, we de-noise the infrared thermal images by median filtering algorithm. Then we propose two time-series temperature features: the crossing temperature feature and the temperature difference feature, and compared their robustness. We perform hyper-parameter search by grid search and random search, for KNN, SVM and random forest. Experiments prove that the temperature difference feature is effective in this study. The KNN based on grid search can achieve 100% accuracy. The SVM has the highest classification efficiency, that based on grid search and random search can achieve 100% classification accuracy in 0.63 s and 0.78 s, respectively.

An efficient malicious webpage static detection framework based on optimized Bayesian and hybrid machine learning

SummaryMalicious webpage detection is a crucial work in both theory and practical environment. In practical applications, static detection methods are usually regarded as a priority choice, which can quickly detect unknown malicious web pages and avoid a costly in‐depth analysis. However, existing solution of static detection typically has the following problems. For example, a single static detection may lead to a higher false positive rate, and the integrated detection usually has a lower detection efficiency. In this article, we propose an efficient webpage static detection framework, especially considering both the detection efficiency and the detection accuracy. Then, on the basis of the extended feature sets from URL, HTML, and JavaScript, we introduce an optimized naive Bayesian algorithm, in which a novel amplification factor strategy is proposed. Finally, a webpage threat assessment model oriented to general machine learning is presented to achieve the refined detection. Three main properties are provided: high detection efficiency, high detection accuracy, and better applicability. Furthermore, the comprehensive experimental results and comparative analysis is given to show the advantages of the proposed framework.

The polarization sensitivity of GRETINA

Compton polarimeters have played an important role in the study of nuclear structure physics, but have often been limited in their applications because of relatively low γ-ray detection efficiency. With the advent of γ-ray tracking detector arrays, which feature nearly 4π solid angle coverage and the ability to identify the location of Compton-scattering events to within a few millimeters, this limitation can be overcome. Here we present a characterization of the performance of the Gamma Ray Energy Tracking In-beam Nuclear Array (GRETINA) as a Compton polarimeter using the 24Mg(p,p′) reaction at 2.45 MeV proton energy. We also discuss a new capability added to the simulation package UCGretina to simulate the emission of polarized photons, and compare it to the measured data. Finally, we use these simulations to predict the performance of the Gamma Ray Energy Tracking Array (GRETA).

A feature fusion enhanced multiscale CNN with attention mechanism for spot-welding surface appearance recognition

As the most important welding method in the welding process of automobile body-in-whites, resistance spot welding still relies on manual inspection of appearance quality to eliminate unqualified products, which leads to a low detection efficiency and a high error rate. In response to this problem, the modular design method is adopted in this paper and a multiscale convolution assemble block is proposed firstly, which can effectively distinguish the differences in similar welding spots. Then a dual-use attention block is designed to calibrate the spatial and channel information of welding spot feature maps, so that the model can pay more attention to the valid welding spot features. Several such multiscale blocks with attention mechanism are stacked to generate the main body of the convolutional neural network (CNN) for welding spot appearance recognition. Finally, the de-pooling and feature fusion strategies are used to further improve the computational efficiency and precision, and the model is named AcmNet. The results of classification experiments demonstrated that the proposed strategies are efficient and the accuracy of AcmNet is 95.2%, which is higher than the existing models and very suitable for the body-in-white production lines.

Fast wireless sensor for anomaly detection based on data stream in an edge-computing-enabled smart greenhouse

Edge-computing-enabled smart greenhouses are a representative application of the Internet of Things (IoT) technology, which can monitor the environmental information in real-time and employ the information to contribute to intelligent decision-making. In the process, anomaly detection for wireless sensor data plays an important role. However, the traditional anomaly detection algorithms originally designed for anomaly detection in static data do not properly consider the inherent characteristics of the data stream produced by wireless sensors such as infiniteness, correlations, and concept drift, which may pose a considerable challenge to anomaly detection based on data stream and lead to low detection accuracy and efficiency. First, the data stream is usually generated quickly, which means that the data stream is infinite and enormous. Hence, any traditional off-line anomaly detection algorithm that attempts to store the whole dataset or to scan the dataset multiple times for anomaly detection will run out of memory space. Second, there exist correlations among different data streams, and traditional algorithms hardly consider these correlations. Third, the underlying data generation process or distribution may change over time. Thus, traditional anomaly detection algorithms with no model update will lose their effects. Considering these issues, a novel method (called DLSHiForest) based on Locality-Sensitive Hashing and the time window technique is proposed to solve these problems while achieving accurate and efficient detection. Comprehensive experiments are executed using a real-world agricultural greenhouse dataset to demonstrate the feasibility of our approach. Experimental results show that our proposal is practical for addressing the challenges of traditional anomaly detection while ensuring accuracy and efficiency.

Research on the Region-Growing and Segmentation Technology of Micro-Particle Microscopic Images Based on Color Features

Silkworm microparticle disease is a legal quarantine standard in the detection of silkworm disease all over the world. The current common detection method, the Pasteur manual microscopy method, has a low detection efficiency all over the world. The low efficiency of the current Pasteur manual microscopy detection method makes the application of machine vision technology to detect microparticle spores an important technology to advance silkworm disease research. For the problems of the low contrast, different illumination conditions and complex image background of microscopic images of the ellipsoidal symmetrical shape of silkworm microparticle spores collected in the detection solution, a region growth segmentation method based on microparticle color and grayscale information is proposed. In this method, the fuzzy contrast enhancement algorithm is used to enhance the color information of micro-particles and improve the discrimination between the micro-particles and background. In the HSV color space with stable color, the color information of micro-particles is extracted as seed points to eliminate the influence of light and reduce the interference of impurities to locate the distribution area of micro-particles accurately. Combined with the neighborhood gamma transformation, the highlight feature of the micro-particle target in the grayscale image is enhanced for region growing. Mea6nwhile, the accurate and complete micro-particle target is segmented from the complex background, which reduces the background impurity segmentation caused by a single feature in the complex background. In order to evaluate the segmentation performance, we calculate the IOU of the microparticle sample image segmented by this method with its corresponding true value image, and the experiments show that the combination of color and grayscale features using the region growth technique can accurately and completely segment the microparticle target in complex backgrounds with a segmentation accuracy IOU as high as 83.1%.

Micro pin header defect detection system based on OpenCV

In order to solve the problems of low detection efficiency and large detection error in the process of manual quality inspection, a full-automatic defect detection system is built. The system uses an industrial camera, selects a suitable light source for image acquisition, uses the open source OpenCV visual library for image processing and defect contour recognition, and sets the screening conditions for unqualified products. The system can detect whether the needle arrangement has defects in real time and classify them according to different defect categories, It can greatly improve the detection efficiency of needle arranging production enterprises. Through a large number of experimental tests, the detection success rate can reach 98.67%, which shows that the system is feasible.

COVID-19 diagnosis prediction using classical-to-quantum ensemble model with transfer learning for CT scan images

ABSTRACT At present, there are problems of low detection efficiency and accuracy in chest CT images of COVID-19 as well as limited computational power of deep learning model training. Developing a classical-to-quantum (CQ) ensemble model with transfer learning to efficiently detect patients with COVID-19 using chest CT images.: Attributes were extracted from chest CT scans using pre-trained networks ResNet50, VGG16 and AlexNet, while dressed quantum circuits were used as classifiers. The overall accuracy of the CQ method based on three aforementioned networks on the chest CT dataset is 83.2%, 86.2% and 85.0%, respectively. The proposed ensemble model has a precision of 89.0% for pneumonia samples, an overall accuracy of 88.6% and a pneumonia class recall rate of 83.0%. In addition, to further verify the robustness of the ensemble model, breast ultrasound and brain tumour images were used in it. The suggested ensemble approach is effective for classifying and detecting medical pictures with complicated features, particularly for detecting COVID-19 patients using chest CT images.

Research on 3D medical image surface reconstruction based on data mining and machine learning

Three-dimensional (3D) medical images are prone to overlap, and there are some problems, such as low detection efficiency and inconsistent with the actual situation. Therefore, a 3D medical image surface reconstruction method based on data mining and machine learning is proposed. The 3D medical images were classified according to different ways, the information frame of 3D medical images was established and the surface overlapping information model of 3D images was given. Based on this information framework, the nonlinear function of overlapping area information of 3D medical images was constructed. The weight of the nonlinear function was used to calculate the input and output results of overlapping area information. Combined with the input mode of 3D medical image information, the error between the information output and the expected output was set. The nonlinear function weight of the overlapping area information of 3D medical images was modified by using the learning rate and the use time of the overlapping area information, and the influence factors of the overlapping information detection were obtained by increasing the situation terms, so as to complete the detection of the surface reconstruction information of 3D medical images. The experimental results show that the information detection results of the proposed method fit well with the actual situation, and the information detection efficiency is high.

Integrity in Organization to Prevent Criminal Liability – Integrity Theory in Criminal Prophylaxis Approach

Crime prevention is an obligation of a state. However, there are special areas where the state is unable to perform this obligation effectively on its own, therefore the difficulty of detection results in increased latency for specific crimes. Low detection efficiency motivates the continuation of commit these crimes, even if the legislator envisages high sanctions for the commission of the given conduct. Crudely sanctions would only act as a deterrent if the perpetrator of the crime could reasonably fear unconditional prosecution because of the high detection potential of the act. In the absence of this, increasing sanctions is not an optimal means of reducing latency, and thus of crime prevention. Such an area of detection challenge is also crime within the organization, as due to the closed, hierarchical structure of the organization, it is suitable to reveal illegal behaviors committed within its framework to the outside world, and thus to law enforcement authorities. It is therefore in the fundamental interest of the state to encourage organizations to prevent abuses within their framework, even if they otherwise serve the interests of the organization. The integrity approach promotes the morally clean operation of the organization and the individuals that are part of it, thus it is also a suitable system of tools to prevent the typically latent economic and corruption crimes committed within the organization. The study deals with organizational integrity in a criminological, more narrowly, crime prevention approach. After formulating the meaning of integrity from a criminological point of view, it deals with the relationship between integrity and compliance, and then with the question of what motivating factors make the organization to a source of danger at all, to a criminogenic area, and how to eliminate these factors. The final chapter of the study addresses the crime prevention relevance of integrity management tools.

Analysis of Proteomic Characteristics of Peripheral Blood in Preeclampsia and Study of Changes in Fetal Arterial Doppler Parameters Based on Magnetic Nanoparticles

Background Traditional mass spectrometry detection methods have low detection efficiency for low-abundance proteins, thus limiting the application of proteomic analysis in the diagnosis of preeclampsia. Magnetic nanomaterials have good superparamagnetism and have obvious advantages in the field of biological separation and enrichment. Aim The objective of this study is to explore the value of superparamagnetic iron oxide nanoparticles in the proteomic analysis of preeclampsia. Materials and Methods 42 patients and 40 normal pregnant women were selected in this study for analysis. Gene Ontology enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were performed to evaluate the function of these differential proteins. Proteomic analysis was used to analyze the differential proteins. Color Doppler ultrasound technology was used to detect changes in the blood flow of the fetal umbilical artery and cerebral artery. Results 16 differential proteins in the serum of pregnant women with preeclampsia and normal pregnant women were detected. The 16 proteins are mainly related to angiogenesis and endothelial function proteins, coagulation cascade proteins, placental growth factor, and so on. Biological function analysis revealed that these proteins are mainly enriched in the nuclear factor kB (NF-κB) signaling pathway. Moreover, our data suggested that compared with the fetus in the uterus of normal pregnant women, the umbilical artery S/D, PI, and RI of the fetus in preeclampsia were greatly increased, and the cerebral artery S/D, PI, and RI were greatly decreased. Conclusion Biological function analysis revealed that 16 proteins are mainly enriched in the NF-κB signaling pathway. Compared with the normal group, the umbilical artery S/D, PI, and RI of the preeclampsia group were greatly increased, and the cerebral artery S/D, PI, and RI were all greatly reduced. Our findings provided a more comprehensive reference for us to study the mechanism of preeclampsia at the molecular level and also provide data support for the screening of relevant markers for early diagnosis of preeclampsia.

Control and application of ultra-high voltage insulator cleaning and detecting robot

With the development of global energy Internet and demand for UHV transmission, uHV transmission lines will increase rapidly and become more and more important for national economic development. The uHV transmission lines will increase year by year and become increasingly important to the economic development of the country. It is necessary to study the cleaning and detection technology of transmission line insulators that the insulators of UHVDC transmission lines such as large leakage rate, low detection efficiency and difficult cleaning of insulators. Therefore, the development of uhv transmission line insulator hot-line cleaning robot and detection integration has important engineering significance and practical value to improve the level of the operation of the uhv power transmission engineering maintenance, safe and reliable operation of the protection of uhv transmission lines. In this paper, the research on the integrated robot for live cleaning and detection of uHV transmission line insulators will greatly promote the live operation of UHV transmission lines in China. It can be directly applied to the live operation of UHV DC and can be promoted nationwide.

Surface Detection of Solid Wood Defects Based on SSD Improved with ResNet

Due to the lack of forest resources in China and the low detection efficiency of wood surface defects, the output of solid wood panels is not high. Therefore, this paper proposes a method for detecting surface defects of solid wood panels based on a Single Shot MultiBox Detector algorithm (SSD) to detect typical wood surface defects. The wood panel images are acquired by an independently designed image acquisition system. The SSD model included the first five layers of the VGG16 network, the SSD feature mapping layer, the feature detection layer, and the Non-Maximum Suppression (NMS) module. We used TensorFlow to train the network and further improved it on the basis of the SSD network structure. As the basic network part of the improved SSD model, the deep residual network (ResNet) replaced the VGG network part of the original SSD network to optimize the input features of the regression and classification tasks of the predicted bounding box. The solid wood panels selected in this paper are Chinese fir and pine. The defects include live knots, dead knots, decay, mildew, cracks, and pinholes. A total of more than 5000 samples were collected, and the data set was expanded to 100,000 through data enhancement methods. After using the improved SSD model, the average detection accuracy of the defects we obtained was 89.7%, and the average detection time was 90 ms. Both the detection accuracy and the detection speed were improved.

Molecularly imprinted polydopamine coated CdTe@SiO2 as a ratiometric fluorescent probe for ultrafast and visual p-nitrophenol monitoring

Molecular imprinted ratiometric fluorescent analysis method has been a popular method for the quantitative and qualitative tests of target analysis yet encounters low detection efficiency caused by the deep embedment and uneven distribution of fluorescent monomers, even the embedding rate of fluorescent monomer directly affects the visual detection effect. Herein, the ratiometric fluorescent molecularly imprinted polymers (F-PDA/CdTe QDs@SiO2@MIPs) based fluorescent polydopamine (F-PDA) and CdTe quantum dots (CdTe QDs) was successfully synthesized to detect p-nitrophenol (p-NP) selectively and visually. F-PDA was firstly used in the synthesis of ratiometric fluorescent molecularly imprinted polymers to serve as both fluorescent monomer and functional monomer, which greatly shorten the detection time while reducing the fluorescence loss caused by polymer coating. The test results showed that the p-NP quenched the fluorescent of F-PDA via electron transfer. Meanwhile, F-PDA/CdTe QDs@SiO2@MIPs enabled to visually detect a low detection limit of p-NP (56.68 nM) within 2.0 min by naked eyes. The detection time was as fast as quantum dots detect targets directly and the detection limit was well below the standard concentration of p-NP in drinking water. Finally, the F-PDA/CdTe QDs@SiO2@MIPs realize the detection of p-NP in the drinking and wastewater respectively.