Analysis of the joint detection capability of the SMILE satellite and EISCAT-3D radar

The Solar wind Magnetosphere Ionosphere Link Explorer(SMILE)satellite is a small magnetosphere–ionosphere link explorer developed cooperatively between China and Europe.It pioneers the use of X-ray imaging technology to perform large-scale imaging of the Earth’s magnetosheath and polar cusp regions.It uses a high-precision ultraviolet imager to image the overall configuration of the aurora and monitor changes in the source of solar wind in real time,using in situ detection instruments to improve human understanding of the relationship between solar activity and changes in the Earth’s magnetic field.The SMILE satellite is scheduled to launch in 2025.The European Incoherent Scatter Sciences Association(EISCAT)-3D radar is a new generation of European incoherent scatter radar constructed by EISCAT and is the most advanced ground-based ionospheric experimental device in the high-latitude polar region.It has multibeam and multidirectional quasi-real-time three-dimensional(3D)imaging capabilities,continuous monitoring and operation capabilities,and multiple-baseline interferometry capabilities.Joint detection by the SMILE satellite and the EISCAT-3D radar is of great significance for revealing the coupling process of the solar wind–magnetosphere–ionosphere.Therefore,we performed an analysis of the joint detection capability of the SMILE satellite and EISCAT-3D,analyzed the period during which the two can perform joint detection,and defined the key scientific problems that can be solved by joint detection.In addition,we developed Web-based software to search for and visualize the joint detection period of the SMILE satellite and EISCAT-3D radar,which lays the foundation for subsequent joint detection experiments and scientific research.

Deep Learning-Based Two-Step Approach for Intrusion Detection in Networks

Intrusion Detection Systems (IDS) are essential for computer security, with various techniques developed over time. However, many of these methods suffer from high false positive rates. To address this, we propose an approach utilizing Recurrent Neural Networks (RNN). Our method starts by reducing the dataset’s dimensionality using a Deep Auto-Encoder (DAE), followed by intrusion detection through a Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed DAE-BiLSTM model outperforms Random Forest, AdaBoost, and standard BiLSTM models, achieving an accuracy of 0.97, a recall of 0.95, and an AUC of 0.93. Although BiLSTM is slightly less effective than DAE-BiLSTM, both RNN-based models outperform AdaBoost and Random Forest. ROC curves show that DAE-BiLSTM is the most effective, demonstrating strong detection capabilities with a low false positive rate. While AdaBoost performs well, it is less effective than RNN models but still surpasses Random Forest.

基于NVAE和OB-Mix的小样本数据增强方法

由于深度学习模型对海量标注数据的依赖性较高,导致目前许多前沿性目标检测理论难以适用于工业检测领域。为此,提出一种基于NVAE图像生成和OB-Mix数据增强的小样本数据扩充方法。具体方法是通过NVAE构建检测目标的数据分布模型,再通过采样潜变量的方式生成与真实目标图像属于同一分布的全新目标图像。在得到生成目标图像后,提出了OB-Mix数据增强策略,将生成目标图像与背景图像进行随机位置融合以构建出新的图像数据,从而提高网络的定位能力及泛化能力。方法在仅使用474张标注图像以及400张无检测目标的背景图像情况下,使YOLOv5的检测精确率达到95.86%,相比于不使用该方法的结果提高了17.60个百分点。

3D cavity detection technique and its application based on cavity auto scanning laser system

Ground constructions and mines are severely threatened by ones. Safe and precise cavity detection is vital for reasonable cavity underground cavities especially those unsafe or inaccessible evaluation and disposal. The conventional cavity detection methods and their limitation were analyzed. Those methods cannot form 3D model of underground cavity which is used for instructing the cavity disposal; and their precisions in detection are always greatly affected by the geological circumstance. The importance of 3D cavity detection in metal mine for safe exploitation was pointed out; and the 3D cavity laser detection method and its principle were introduced. A cavity auto scanning laser system was recommended to actualize the cavity 3D detection after comparing with the other laser detection systems. Four boreholes were chosen to verify the validity of the cavity auto scanning laser system. The results show that the cavity auto scanning laser system is very suitable for underground 3D cavity detection, especially for those inaccessible ones.

Multi-features Based Approach for Moving Shadow Detection

In the video-based surveillance application, moving shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for shadow detection and suppression used for moving visual object detection. The major novelty of the shadow suppression is the integration of several features including photometric invariant color feature, motion edge feature, and spatial feature etc. By modifying process for false shadow detected, the averaging detection rate of moving object reaches above 90% in the test of Hall-Monitor sequence.

Clinical significance of serum tumor markers CA153, CA125, CA72-4 and FIB, IL-6 levels detection in ovarian cancer

Objective: To investigate the clinical significance of serum tumor markers CA153, CA125, CA72-4 and FIB, IL-6 levels in the detection of ovarian cancer. Methods: A total of 40 patients with ovarian carcinoma treated in our hospital from September 2015 to June 2017 were selected as the ovarian cancer group;40 patients with benign ovarian tumors in the same period were selected as the benign ovarian tumor group;40 healthy subjects were selected as the control group. The levels of tumor markers CA153, CA125, CA72-4 and FIB, IL-6 were compared between the three groups. Results: The CA153, CA125, CA72-4 and FIB, IL-6 levels of the ovarian cancer group were significantly higher than those in benign ovarian tumor group and the control group;these levels in the benign ovarian tumor group was not significantly different from those in the control group. With the increase of clinical phase, the levels of CA153, CA125 and CA72-4 in patients with ovarian cancer were gradually increased, and the levels in phase Ⅲ and Ⅳ were significantly higher than those in phase Ⅱ and in phase I;and the CA125 in phase Ⅱ was significantly higher than that in phase Ⅰ. The levels of FIB and IL-6 in phase Ⅱ and in phase Ⅲ, Ⅳ were significantly higher than those in phase I;the IL-6 level in phase Ⅲ, Ⅳ was significantly higher than that in phase Ⅱ. Conclusion: Serum tumor markers CA153, CA125, CA72-4 and FIB, IL-6 levels for ovarian cancer detection can be helpful for clinical diagnosis and worthy of promotion.

Moving Target Detection and Tracking for Smartphone Automatic Focusing

In this paper,a non-contact auto-focusing method is proposed for the essential function of auto-focusing in mobile devices.Firstly,we introduce an effective target detection method combining the 3-frame difference algorithm and Gauss mixture model,which is robust for complex and changing background.Secondly,a stable tracking method is proposed using the local binary patter feature and camshift tracker.Auto-focusing is achieved by using the coordinate obtained during the detection and tracking procedure.Experiments show that the proposed method can deal with complex and changing background.When there exist multiple moving objects,the proposed method also has good detection and tracking performance.The proposed method implements high efficiency,which means it can be easily used in real mobile device systems.

基于VAE-LSTM模型的无人机飞行数据异常检测

无人机飞行数据是反映其自身飞行安全的重要状态参数,通过对飞行数据进行异常检测,是提高无人机整体飞行安全性的关键举措。尽管基于数据驱动方法不需专家先验知识和精确的物理模型,但缺乏参数选择且检测网络结构模型单一,使得检测模型由于参数过多导致过拟合以及无法有效捕捉数据异常模式的问题。文中结合变分自编码器和长短期记忆网络的优势,提出了一种基于VAE-LSTM的无人机飞行数据异常检测模型方法。首先,引入肯德尔相关性分析方法用于选择相关依赖的飞行数据参数集;其次,将具有相关性的参数集对所设计的VAE-LSTM深度混合模型进行训练,学习不同数据特征之间的关系映射;最后,以无监督异常检测方式在真实多维无人机飞行数据进行验证。实验结果表明,VAE-LSTM的精密度、检测率、准确率、F1分数及误检率的各项平均性能指标分别达到95.24%、98.71%、98.8%、96.82%、1.31%,相比于KNN、OC-SVM、VAE、LSTM模型,整体上展现出较好异常检测性能。

BACKGROUND RECTIFICATION AND FEATURE EXTRACTION OF IMAGE IN A SPOT WELD OF AL ALLOY X-RAY DETECTION

A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.

Obstacle detection using multi-sensor fusion

This paper presents an obstacle detection approach for blind pedestrians by fusing data from camera and laser sensor.For purely vision-based blind guidance system,it is difficult to discriminate low-level obstacles with cluttered road surface,while for purely laser-based system,it usually requires to scan the forward environment,which turns out to be very inconvenient.To overcome these inherent problems when using camera and laser sensor independently,a sensor-fusion model is proposed to associate range data from laser domain with edges from image domain.Based on this fusion model,obstacle's position,size and shape can be estimated.The proposed method is tested in several indoor scenes,and its efficiency is confirmed.

5-(2-Hydroxylphenyl)diazo-dipyrromethane:Synthesis,Structure and Fluoride Ion Detection

A new azopyrrole compound, 1, has been synthesized and characterized. The crystal of 1 is of monoclinic system, space group P21/c with a = 8.7167（9）, b = 17.5929（19）, c = 12.8096（15） ？, β = 97.565（2）o, V = 1947.3（4） ^3, Z = 4, C（20）H（26）N4O2, Mr = 354.45, Dc = 1.209 g/cm^3, F（000） = 760 and μ（Mo Kα） = 0.080 mm^-1. In the crystal, 1 binds one methanol molecule through N–H…O, O–H…O and O–H…π interactions. UV-Vis titration and 1H NMR titration studies reveal that compound 1 can selectively detect fluoride ion in the DMSO solution.

基于自相关-变分对抗学习的物理系统异常检测

传统时间序列异常检测模型在处理信息物理系统(CPS)中的多元传感器和执行器数据时,难以准确提取多元数据之间的时序联系,从而影响异常检测性能。为此,提出一种新的时间序列异常检测方法,称为自相关-变分自编码(VAE)-对抗学习网络AMVG。以生成对抗网络(GAN)为基础,使用Noise数据增强方法扩展训练数据量,并通过引入自相关矩阵增强数据依赖关系,结合VAE的数据重建能力,在加强模型鲁棒性的同时进一步提高异常检测模型性能,由AMVG 2个解码器构成互相对抗的G网络和D网络,G网络和D网络不断对抗训练优化模型的检测能力。在3个真实世界的CPS数据集上的实验结果表明,AMVG方法相较于最新研究方法在精确率、召回率以及F1值等综合性能上均取得显著提高,AMVG在3个数据集上的F1值分别为0.953、0.758、0.891,其中较次优USAD和GRELEN的F1值最低可提高6.2、3.4、7.5个百分点。

Significance of combined detection of serum 25(OH)D3, hsa-miR-17-5p and HCV-RNA in the diagnosis of hepatitis C disease

Objective: Significance of combined detection of serum 25(OH)D3, hsa-miR-17-5p and HCV-RNA in diagnosis of hepatitis C disease. Methods: A total of 52 patients with benign ovarian tumor resection were selected from April 2016 to April 2018 in our hospital. We paid attention to the implementation of perioperative nursing intervention, and observed the prognosis and the occurrence of adverse reactions. Results: The expression of hsa-mir-17-5p in the observation group was significantly higher than that in the control group, the expression of 25(OH)D3 was lower than that in the control group, the expression of hsa-mir-17-5p in the HCV-RNA positive group was higher than that in the HCV-RNA negative group, and the expression of 25(OH) D3 was lower than that in the HCV-RNA negative group. The expression of HCV-RNA in the observation group was positively and negatively correlated with the expression of 25(OH) D3 and hsa-mir-17-5p in the 25(OH)D3 and the critical values of serum 25 (OH)D3, hsa-mir-17-5p and HCV-RNA were 24.23 ug/L, 1.89 relative expression and 1.22 × 103 IU/mL, respectively. The area of AUC detected by hsa-miR-17-5p+ 25 (OH) D3+25(OH)D3 is larger than that detected separately. Conclusion: The combined detection of serum 25(OH)D3, hsa-mir-17-5p and HCV-RNA has high diagnostic efficiency and sensitivity for hepatitis C. It is suggested that they be used in clinical practice.

基于BiLSTM-DAE的多家族恶意域名检测算法

针对现有恶意域名检测算法对于家族恶意域名检测精度不高和实时性不强的问题,提出一种基于BiLSTM-DAE的恶意域名检测算法。通过利用双向长短时记忆神经网络(Bi-directional Long Short Term Memory,BiLSTM)提取域名字符组合的上下文序列特征,并结合深度自编码网络(Deep Auto-Encoder,DAE)逐层压缩感知提取类内有共性和类间有区分性的强字符构词特征并进行分类。实验结果表明,与当前主流恶意域名检测算法相比,该算法在保持检测开销较小的基础上,具有更高的检测精度。

基于IWOA-ELM-AE的电力资产信息管理系统异常数据检测方法

针对当前电力资产信息管理系统难以准确自主发现异常数据的问题,提出了一种基于IWOA-ELM-AE的电力资产信息管理系统异常数据检测方法。在管理系统框架下分析了可能存在的异常类型,将改进鲸鱼优化算法(IWOA)用于优化极限学习机自编码器(ELM-AE),建立了电力信息系统异常数据优化检测模型。将模型应用于电力资产信息异常数据检测,并建立性能评估指标体系以衡量其效果。结果表明:所提方法的检测性能评估结果与传统模型相比具有显著优势,能够更为准确地检测电力资产信息中存在的异常数据。

基于改进LSTM-VAE的配电网异常负荷检测方法研究

针对目前配电网负荷数据异常检测方法准确率低的问题,提出将改进的长短期记忆网络和变分自编码器相结合用的配电网负荷异常检测方法。通过残差结构对长短期记忆网络进行优化,提高特征学习能力,并将优化后的长短期记忆网络替换变分自编码器的BP神经网络层(编码和解码),可以更好地获得负荷数据的时间相关性。通过与常规检测方法的试验对比,验证了所提检测方法的优越性。结果表明,相比于常规负荷数据异常检测方法,所提方法具有更好的检测准确率,异常检测准确率为97.30%,比未引入残差结构提高了1.70%,比LSTM模型提高了7.00%,比PSO-PFCM模型提高了4.80%。可为配电网自动化的发展提供一定的参考。

Investigation on the Structure of Chute-feed and Card Auto-leveller and Their Selection of Technological Processes

Based on the structure of chute - feed and autoleveHer, an analysis of their working principle and the verification of their practical production results have been carried out. Finally, the future investigation direetiom of chute - feed and card autuleveller are put forward.

基于LTE-R无线网络的电力机车运行状态远程检测与自动控制研究

为避免电力机车异常行为带来的行车风险,提出基于LTE-R无线网络的电力机车运行状态远程检测与自动控制方法。首先采集模块获取电力机车运行状态信号,将其使用信号调理电路转换为优质数字信号后,运用LTE-R无线网络传输到地面监控模块,该模块负责提取所接收数字信号的特征,并依据特征采用长短时记忆神经网络远程检测电力机车运行状态,同时在发生异常行为时通过自动控制发出报警。实验结果表明:不同通信距离下,LTE-R无线网络各通信信道的信号强度均稳定在-6 dBm以上,在准确检测电力机车运行状态的同时,还能完成有效报警。

基于单幅图像形状特征的三维漫画人脸重建

针对单幅图像的三维漫画人脸重建存在地标检测准确性差和生成模型还原高频细节能力低的问题,提出了一种多尺度特征融合与高频信息映射的两阶段方法。在第一阶段中,多尺度通道融合地标检测器用于提高检测的准确性。其中多尺度特征由HRNet产生;由通道注意力和Swin Transformer构成的注意力层用于多尺度通道融合特征提取;为了提高生成地标的精度,损失函数由地标损失和热图损失两部分构成。在第二阶段中,傅里叶特征共享层变形网络使生成的三维漫画人脸具有更丰富的高频形状细节。其中傅里叶特征映射提取高维特征,使网络学习更多形状的高频信息;共享层超网络加快了网络的收敛和重建速度。该方法应用于CaricatureFace和3DCaricShop数据集。实验结果表明,该方法中的地标检测器的平均检测误差减少了4.4%;变形网络在形状重建上的均方误差减少了26%,并且平均重建时间减少了18%;最终重建出的三维漫画人脸具有夸张的形状和自然的细节。

自动固相微萃取(SPM E)GC-MS、GC-MS-MS法检测环境水中有机磷杀虫剂的研究

固相微萃取(solid-phase microextraction,SPME)是20世纪90年代发展起来的一种样品前处理技术,与传统的液-液提取、液-固提取相比,SPME更适用于提取、浓缩液态或气态的挥发性和半挥发性物质,SPME技术可将采样、萃取、浓缩和样本引入集中于一个步骤完成,尤其随着自动SPME与GC-MS等联用技术的日益完善,使SPME技术优点得到更充分的发挥.……