Real-time Rescue Target Detection Based on UAV Imagery for Flood Emergency Response

Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including high-resolution imagery and exceptional mobility,making them well suited for monitoring flood extent and identifying rescue targets during floods.However,there are some challenges in interpreting rescue information in real time from flood images captured by UAVs,such as the complexity of the scenarios of UAV images,the lack of flood rescue target detection datasets and the limited real-time processing capabilities of the airborne on-board platform.Thus,we propose a real-time rescue target detection method for UAVs that is capable of efficiently delineating flood extent and identifying rescue targets(i.e.,pedestrians and vehicles trapped by floods).The proposed method achieves real-time rescue information extraction for UAV platforms by lightweight processing and fusion of flood extent extraction model and target detection model.The flood inundation range is extracted by the proposed method in real time and detects targets such as people and vehicles to be rescued based on this layer.Our experimental results demonstrate that the Intersection over Union(IoU)for flood water extraction reaches an impressive 80%,and the IoU for real-time flood water extraction stands at a commendable 76.4%.The information on flood stricken targets extracted by this method in real time can be used for flood emergency rescue.

A CNN-Based Single-Stage Occlusion Real-Time Target Detection Method

Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.

4种植物源性成分多重real-time PCR检测方法的建立及其在食用淀粉中的应用

建立一种可同时快速检测红薯、木薯、马铃薯、玉米源性成分的多重实时聚合酶链式反应(real-time polymerase chain reaction,real-time PCR)方法。分别以红薯g3pdh基因、木薯g3pdh基因、马铃薯UGPase基因、玉米zSSIIb基因为靶基因设计特异性引物和TaqMan探针,以18S rRNA基因为内参基因,建立多重real-time PCR方法,开展方法学验证,并对不同掺入比例模拟样品和实际淀粉样品进行检测。结果显示,该方法具有高通量、特异性强、灵敏度高等优点。与15种非目标源性均无交叉反应;对目标DNA的检测灵敏度可达到3×10^(-3) ng/μL,且具有良好的线性关系和扩增效率;对淀粉样品的检出限可达0.1%,对50份实际样品进行检测,结果与参比方法一致,说明建立的多重real-time PCR法可用于食用淀粉种类掺假鉴别检测。

Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

基于Real-time PCR法检测乳粉中牛源性成分定量研究

基于Real-timePCR建立了乳粉中牛源性成分相对定量检测方法,并对牛的特异性引物与探针进行了特异性、灵敏度和稳定性测试。通过模拟不同浓度牛乳粉与马乳粉混合样本,根据其△Ct值的函数关系进行线性拟合进而绘制标准曲线,建立乳粉中牛源性成分的相对定量检测。结果显示,该方法的最低检测限为0.00001 mg/mL,回收率为91.11%~119.2%,组间变异系数≤0.58%、组内变异系数≤1.44%。说明该方法在特异性与稳定性上适用于乳粉中牛源性成分及含量的掺假检测。

基于病菌孢子捕捉和real-time PCR技术的田间空气中小麦白粉病菌孢子动态监测及病情估计模型研究

利用Burkard定容式孢子捕捉器结合real-time PCR定量技术,分别对种植高抗、中感和高感白粉病小麦品种的田间空气中白粉病菌分生孢子浓度进行监测,结果表明,real-time PCR定量与传统的显微观察计数两种方法测得的孢子浓度呈显著正相关(P≤0.01),且两种病菌孢子计数方法在同一抗性品种上监测到的孢子浓度动态相近。此外,两种方法测得的孢子浓度与各气象因子的相关性分析结果一致,空气中的白粉病菌孢子浓度主要与空气相对湿度显著正相关。在此基础上,利用两种方法测定的田间空气中白粉病菌孢子浓度分别建立了基于累积孢子浓度的田间病情估计模型。分析发现,基于两种孢子浓度测定方法建立的病情估计模型间无显著性差异,表明real-time PCR定量技术测定的孢子浓度在构建白粉病病情估计模型上具有一定可行性。该结果为real-time PCR定量技术与病菌孢子捕捉技术相结合用于小麦白粉病的监测和预测提供理论依据。

一种基于real-time PCR技术的TTV检测方法的建立及应用

目的:本研究旨在开发一种具有更高灵敏度和特异性的TTV检测技术,为揭示TTV在多种疾病过程中的作用提供重要的技术支持。方法:为了更精确、灵敏的检测TTV,本研究分析了目前公布的所有亚型的TTV基因序列,在此基础上建立了一种基于UTR区域的real-time PCR检测方法,并与文献报道应用较为广泛的PCR检测方法进行了对比。结果:本研究建立的方法在1×10^(7)~1×10^(1) copies/μL标准品浓度范围内具有良好的线性关系,相关系数为1.000,斜率为-3.446,检测下限为1×10^(1) copies/μL。重复性试验结果显示,组内变异系数为7.22%,表明本方法重复性、稳定性较强。针对30份临床样本,使用本研究建立的real-time PCR检测方法及目前被多个研究所使用的4套引物进行对比。结果表明,本研究所建立的方法灵敏度显著高于文献中报道的4种方法(P<0.01);Sanger测序结果表明,本方法检测出的30份阳性样本均为TTV,检测特异性为100%。结论:本研究采用基于TaqMan探针的real-time PCR检测方法,检测灵敏性高、覆盖基因型范围广,尤其对于TTV病毒载量较低的情况下能够进行定量检测,对于TTV病毒的致病性及作为免疫标志物的应用提供重要的技术支持。

马乳酒样乳杆菌马乳酒样亚种real-time PCR检测方法的建立与应用

本研究建立了一种特异性实时聚合酶链式反应(real-time polymerase chain reaction,real-time PCR)检测方法,根据模式菌株马乳酒样乳杆菌马乳酒样亚种ZW3的16S rDNA序列和全基因组序列设计筛选特异性引物,采用SYBR Green I荧光染料建立real-time PCR方法,并对方法的特异性、灵敏度、重复性和混合体系等进行检测。结果表明,本研究所建立的方法特异性强、灵敏度高、重复性好,建立real-time PCR的标准曲线,其决定系数R2为0.965,具有良好的线性关系,且在马乳酒样乳杆菌马乳酒样亚种及混合体系中可以特异性检出。综上,本研究建立的real-time PCR法可以快速、准确地检测马乳酒样乳杆菌马乳酒样亚种,为马乳酒样乳杆菌的特异性定性定量检测提供了一种新的方法。

Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

Preliminary research and scheme design of deep underground in situ geo-information detection experiment for Geology in Time

The deep earth,deep sea,and deep space are the main parts of the national“three deep”strategy,which is in the forefront of the strategic deployment clearly defined in China’s 14th Five-Year Plan(2021-2025)and the Long-Range Objectives Through the Year 2035.It is important to reveal the evolutionary process and mechanism of deep tectonics to understand the earth’s past,present and future.The academic con-notation of Geology in Time has been given for the first time,which refers to the multi-field evolution response process of geological bodies at different time and spatial scales caused by geological processes inside and outside the Earth.Based on the deep in situ detection space and the unique geological envi-ronment of China Jinping Underground Laboratory,the scientific issue of the correlation mechanism and law between deep internal time-varying and shallow geological response is given attention.Innovative research and frontier exploration on deep underground in situ geo-information detection experiments for Geology in Time are designed to be carried out,which will have the potential to explore the driving force of Geology in Time,reveal essential laws of deep earth science,and explore innovative technologies in deep underground engineering.

A Novel Hybrid Architecture for Superior IoT Threat Detection through Real IoT Environments

As the Internet of Things(IoT)continues to expand,incorporating a vast array of devices into a digital ecosystem also increases the risk of cyber threats,necessitating robust defense mechanisms.This paper presents an innovative hybrid deep learning architecture that excels at detecting IoT threats in real-world settings.Our proposed model combines Convolutional Neural Networks(CNN),Bidirectional Long Short-Term Memory(BLSTM),Gated Recurrent Units(GRU),and Attention mechanisms into a cohesive framework.This integrated structure aims to enhance the detection and classification of complex cyber threats while accommodating the operational constraints of diverse IoT systems.We evaluated our model using the RT-IoT2022 dataset,which includes various devices,standard operations,and simulated attacks.Our research’s significance lies in the comprehensive evaluation metrics,including Cohen Kappa and Matthews Correlation Coefficient(MCC),which underscore the model’s reliability and predictive quality.Our model surpassed traditional machine learning algorithms and the state-of-the-art,achieving over 99.6%precision,recall,F1-score,False Positive Rate(FPR),Detection Time,and accuracy,effectively identifying specific threats such as Message Queuing Telemetry Transport(MQTT)Publish,Denial of Service Synchronize network packet crafting tool(DOS SYN Hping),and Network Mapper Operating System Detection(NMAP OS DETECTION).The experimental analysis reveals a significant improvement over existing detection systems,significantly enhancing IoT security paradigms.Through our experimental analysis,we have demonstrated a remarkable enhancement in comparison to existing detection systems,which significantly strength-ens the security standards of IoT.Our model effectively addresses the need for advanced,dependable,and adaptable security solutions,serving as a symbol of the power of deep learning in strengthening IoT ecosystems amidst the constantly evolving cyber threat landscape.This achievement marks a significant stride towards protecting the integrity of IoT infrastructure,ensuring operational resilience,and building privacy in this groundbreaking technology.

Advancing Autoencoder Architectures for Enhanced Anomaly Detection in Multivariate Industrial Time Series

In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.

A Comparative Study between Landmark Based and Real Time Ultrasound Guided Sub Arachnoid Block

Background: Sub arachnoid block (SAB) performed by traditional landmark palpation technique can be inaccurate. This problem is exacerbated by altered patient anatomy due to obesity and age-related changes. A pre-procedural ultrasound scan of the lumbar spine has been shown to be of benefit in guiding lumbar epidural insertion in obstetric patients. Information on the use of real-time ultrasound (RUS) guided SAB, to date, been limited. This study compared RUS guided SAB to traditional landmark guided technique in patients undergoing spinal anesthesia for different surgical procedures. Methods: This was a prospective, single center, comparative observational study conducted in the department of anesthesiology at our center. 560 patients who underwent spinal anesthesia either by landmark based technique or real-time ultrasound-guided methods. The primary outcome was the first attempt success rate of dural puncture when employing the two methods. Results: Baseline characteristics were similar in the two study groups. The first attempt success rate of dural puncture in landmark guided group was 64.3% compared to 72.6% in the ultrasound guided group. This difference was not statistically significant. The procedure performance time was significantly shorter with landmark palpation compared to use of real-time ultrasound guided method. Conclusion: Use of RUS-guided technique does not significantly improve the first attempt success rate of SAB dural puncture during spinal anesthesia compared to the traditional landmark-guided technique.

Sentiment Drift Detection and Analysis in Real Time Twitter Data Streams

Handling sentiment drifts in real time twitter data streams are a challen-ging task while performing sentiment classifications,because of the changes that occur in the sentiments of twitter users,with respect to time.The growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real time.This work proposes an adap-tive learning algorithm-based framework,Twitter Sentiment Drift Analysis-Bidir-ectional Encoder Representations from Transformers(TSDA-BERT),which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real time.The framework also works on static data by converting them to data streams using the Kafka tool.The experiments conducted on real time and simulated tweets of sports,health care andfinancial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model,with accuracies of 91%,87%and 90%,respectively.Though the results have been provided only for a few topics,as a proof of concept,this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic.

Prevalence and Antibiotic Resistance of Urinary Tract Pathogens, with Molecular Identification of Klebsiella pneumoniae, Klebsiella oxytoca, and Acinetobacter spp., Using Multiplex Real-Time PCR

Urinary tract infections (UTIs) caused by uropathogens are a significant public health problem, and their treatment primarily relies on antibiotic therapy. However, the increasing global development of antibiotic resistance necessitates updating diagnostic techniques to ensure higher sensitivity and specificity, especially with advancements in science and medicine. This study aimed to evaluate the prevalence of UTIs and antibiotic resistance profiles through urine culture, as well as to identify Klebsiella pneumoniae, Klebsiella oxytoca, and Acinetobacter spp. in urine samples using a molecular approach with multiplex real-time PCR. From May 3 to July 25, 2023, at the Pietro Annigoni Biomolecular Research Center (CERBA) and Saint Camille Hospital of Ouagadougou (HOSCO), 209 urine samples collected from patients with suspected UTIs were analyzed using both urine culture and multiplex real-time PCR. Among the 209 patients, 52.15% were male and 47.85% female, with an average age of 46.87 ± 21.33 years. Urine cultures revealed an overall UTI prevalence of 23.44%, with a prevalence of 8.13% in men versus 15.31% in women (P = 0.023). The bacterial prevalence rates were as follows: Escherichia coli (12.92%), Klebsiella spp. (7.18%), Enterobacter cloacae (1.44%), Staphylococcus aureus (0.96%), and other bacteria. Klebsiella spp. demonstrated 100% resistance to Amoxicillin and Amoxicillin/Clavulanic Acid, while Escherichia coli showed 96.2% and 65.4% resistance to Amoxicillin and Amoxicillin/Clavulanic Acid, respectively. PCR analysis of the target bacteria revealed mono-infection prevalence rates of Klebsiella pneumoniae (10.39%), Klebsiella oxytoca (7.79%), and Acinetobacter spp. (7.79%), along with a co-infection prevalence rate of Klebsiella pneumoniae/Acinetobacter spp. (1.30%). This study demonstrated that PCR, with its high sensitivity and specificity, could effectively distinguish Klebsiella pneumoniae from Klebsiella oxytoca and detect Acinetobacter spp. in less than 24 hours—something urine culture alone could not achieve. The relative ease of automating urine PCR testing, combined with its diagnostic accuracy and rapid turnaround time, makes it a valuable addition to modern medical practice for the laboratory diagnosis of UTIs.

24重荧光real-time PCR技术在食物中毒快速检测中的应用

目的:应用24重荧光real-time PCR检测技术快速筛检食物中毒病原菌,结合国家标准中的培养法探讨24重荧光real-time PCR检测技术符合性和应用价值。方法:采用高灵敏度、高特异性的24重荧光real-time PCR检测技术作为中毒病原菌的初筛方法,国标方法进行细菌分离培养,并对分离出的病原菌进行生化鉴定。结果:5份食物中毒患者肛拭子在增菌前检出4份霍乱弧菌核酸(非O1/非O139群,24重荧光real-time PCR),9份患者肛拭子在增菌后检出5株霍乱弧菌(非O1/非O139群,国标培养法),其中包含4份PCR技术初筛阳性样品,两个方法的符合率为80%。所有样本均未检出沙门氏菌、志贺菌、副溶血性弧菌、致泻性大肠埃希菌以及金黄色葡萄球菌。结论:应用24重荧光real-time PCR检测技术同时检测24种常见致病病原菌,能高效锁定中毒病原菌。将其与国标培养法相结合,对临床治疗和食物中毒快速处置能起到积极作用,值得应用和推广。

Real-Time Monitoring of Meteorological Data at In-Situ GCW Remediation Sites

To optimize the self-organization network, self-adaptation, real-time monitoring, remote management capability, and equipment reuse level of the meteorological station supporting the portable groundwater circulation wells, and to provide real-time and effective technical services and environmental data support for groundwater remediation, a real-time monitoring system design of the meteorological station supporting the portable groundwater circulation wells based on the existing equipment is proposed. A variety of environmental element information is collected and transmitted to the embedded web server by the intelligent weather transmitter, and then processed by the algorithm and stored internally, displayed locally, and published on the web. The system monitoring algorithm and user interface are designed in the CNWSCADA development environment to realize real-time processing and analysis of environmental data and monitoring, control, management, and maintenance of the system status. The PLC-controlled photovoltaic power generating panels and lithium battery packs are in line with the concept of energy saving and emission reduction, and at the same time, as an emergency power supply to guarantee the safety of equipment and data when the utility power fails to meet the requirements. The experiment proves that the system has the characteristics of remote control, real-time interaction, simple station deployment, reliable operation, convenient maintenance, and green environment protection, which is conducive to improving the comprehensive utilization efficiency of various types of environmental information and providing reliable data support, theoretical basis and guidance suggestions for the research of groundwater remediation technology and its disciplines, and the research and development of the movable groundwater cycling well monitoring system.

垂体后叶粉中3种动物源性成分多重real-time PCR检测方法的建立及应用

目的基于三重实时聚合酶链式反应(real-time polymerase chain reaction,real-time PCR)技术同时快速检测垂体后叶粉中的猪、牛、羊性动物源性成分。方法采用CTAB法提取样品及对照品DNA,以线粒体基因为靶基因设计并合成三重real-time PCR的引物探针,并对建立方法进行验证,用于检测垂体后叶粉样品是否与标识一致。结果猪、牛、羊源性成分的最低检测浓度为10 pg/μL,采用建立的方法检测3批垂体后叶粉样品,均只检测出猪源性成分。结论建立的方法可用于同时检测垂体后叶粉中的猪、牛、羊源性成分,可为相关工作提供技术支持。