An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation system.The growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative step.However,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection technologies.This paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking lots.First,we develop a novel dataset to fill the gap,as there is a lack of publicly available data.This dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor conditions.Second,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing capabilities.Third,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency response.Experiments show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.

Network Intrusion Traffic Detection Based on Feature Extraction

With the increasing dimensionality of network traffic,extracting effective traffic features and improving the identification accuracy of different intrusion traffic have become critical in intrusion detection systems(IDS).However,both unsupervised and semisupervised anomalous traffic detection methods suffer from the drawback of ignoring potential correlations between features,resulting in an analysis that is not an optimal set.Therefore,in order to extract more representative traffic features as well as to improve the accuracy of traffic identification,this paper proposes a feature dimensionality reduction method combining principal component analysis and Hotelling’s T^(2) and a multilayer convolutional bidirectional long short-term memory(MSC_BiLSTM)classifier model for network traffic intrusion detection.This method reduces the parameters and redundancy of the model by feature extraction and extracts the dependent features between the data by a bidirectional long short-term memory(BiLSTM)network,which fully considers the influence between the before and after features.The network traffic is first characteristically downscaled by principal component analysis(PCA),and then the downscaled principal components are used as input to Hotelling’s T^(2) to compare the differences between groups.For datasets with outliers,Hotelling’s T^(2) can help identify the groups where the outliers are located and quantitatively measure the extent of the outliers.Finally,a multilayer convolutional neural network and a BiLSTM network are used to extract the spatial and temporal features of network traffic data.The empirical consequences exhibit that the suggested approach in this manuscript attains superior outcomes in precision,recall and F1-score juxtaposed with the prevailing techniques.The results show that the intrusion detection accuracy,precision,and F1-score of the proposed MSC_BiLSTM model for the CIC-IDS 2017 dataset are 98.71%,95.97%,and 90.22%.

超声S-Detect技术联合乳腺简化MRI对早期乳腺癌的诊断效能

目的 探讨超声S-Detect技术联合乳腺简化MRI对早期乳腺癌诊断效能的分析。方法 选取2020年1月至2021年12月进行乳腺超声和MRI检查的85个病灶。患者年龄>14岁,且未进行手术及新辅助化疗治疗,肿瘤病灶直径≤2 cm,并进行穿刺或手术获得病理结果。以乳腺穿刺肿瘤病理结果为金标准,评估超声S-Detect技术、乳腺简化MRI及二者联合检查的诊断效能。结果 S-Detect、简化MRI及两者联合诊断的灵敏度分别为:69.5%,81.4%,98.3%,特异度分别为:88.5%,80.8%,76.9%,准确率分别为:75.3%,81.2%,91.8%,与病理一致性检验Kappa值分别为:0.50,0.58,0.80,AUC分别为:0.79,0.81,0.88。差异均有统计学意义(Z=1.979,P<0.05;Z=2.096,P<0.05)。结论 超声S-Detect与乳腺简化MRI技术联合对早期乳腺癌检查的灵敏度、准确率以及与病理一致性比单独使用S-Detect技术或简化MRI高,具有较高的诊断效能,可以对早期乳腺癌的早发现早治疗起到积极作用并为临床科室制定治疗方案提供有效帮助。

Decoding degeneration:the implementation of machine learning for clinical detection of neurodegenerative disorders

Machine learning represents a growing subfield of artificial intelligence with much promise in the diagnosis,treatment,and tracking of complex conditions,including neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases.While no definitive methods of diagnosis or treatment exist for either disease,researchers have implemented machine learning algorithms with neuroimaging and motion-tracking technology to analyze pathologically relevant symptoms and biomarkers.Deep learning algorithms such as neural networks and complex combined architectures have proven capable of tracking disease-linked changes in brain structure and physiology as well as patient motor and cognitive symptoms and responses to treatment.However,such techniques require further development aimed at improving transparency,adaptability,and reproducibility.In this review,we provide an overview of existing neuroimaging technologies and supervised and unsupervised machine learning techniques with their current applications in the context of Alzheimer’s and Parkinson’s diseases.

Detection of Alzheimer’s disease onset using MRI and PET neuroimaging:longitudinal data analysis and machine learning

The scientists are dedicated to studying the detection of Alzheimer’s disease onset to find a cure, or at the very least, medication that can slow the progression of the disease. This article explores the effectiveness of longitudinal data analysis, artificial intelligence, and machine learning approaches based on magnetic resonance imaging and positron emission tomography neuroimaging modalities for progression estimation and the detection of Alzheimer’s disease onset. The significance of feature extraction in highly complex neuroimaging data, identification of vulnerable brain regions, and the determination of the threshold values for plaques, tangles, and neurodegeneration of these regions will extensively be evaluated. Developing automated methods to improve the aforementioned research areas would enable specialists to determine the progression of the disease and find the link between the biomarkers and more accurate detection of Alzheimer’s disease onset.

Lightweight Surface Litter Detection Algorithm Based on Improved YOLOv5s

In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed to provide core technical support for real-time water surface litter detection by water surface litter cleanup vessels.The method reduces network parameters by introducing the deep separable convolution GhostConv in the lightweight network GhostNet to substitute the ordinary convolution in the original YOLOv5s feature extraction and fusion network;introducing the C3Ghost module to substitute the C3 module in the original backbone and neck networks to further reduce computational effort.Using a Convolutional Block Attention Mechanism(CBAM)module in the backbone network to strengthen the network’s ability to extract significant target features from images.Finally,the loss function is optimized using the Focal-EIoU loss func-tion to improve the convergence speed and model accuracy.The experimental results illustrate that the improved algorithm outperforms the original Yolov5s in all aspects of the homemade water surface litter dataset and has certain advantages over some current mainstream algorithms in terms of model size,detection accuracy,and speed,which can deal with the problems of real-time detection of water surface litter in real life.

RT-YOLO:A Residual Feature Fusion Triple Attention Network for Aerial Image Target Detection

In recent years,target detection of aerial images of unmannedaerial vehicle(UAV)has become one of the hottest topics.However,targetdetection of UAV aerial images often presents false detection and misseddetection.We proposed a modified you only look once(YOLO)model toimprove the problems arising in object detection in UAV aerial images:(1)A new residual structure is designed to improve the ability to extract featuresby enhancing the fusion of the inner features of the single layer.At the sametime,triplet attention module is added to strengthen the connection betweenspace and channel and better retain important feature information.(2)Thefeature information is enriched by improving the multi-scale feature pyramidstructure and strengthening the feature fusion at different scales.(3)A newloss function is created and the diagonal penalty term of the anchor frame isintroduced to improve the speed of training and the accuracy of reasoning.The proposed model is called residual feature fusion triple attention YOLO(RT-YOLO).Experiments showed that the mean average precision(mAP)ofRT-YOLO is increased from 57.2%to 60.8%on the vehicle detection in aerialimage(VEDAI)dataset,and the mAP is also increased by 1.7%on the remotesensing object detection(RSOD)dataset.The results show that theRT-YOLOoutperforms other mainstream models in UAV aerial image object detection.

Detection of Different Stages of Alzheimer’s Disease Using CNN Classifier

Alzheimer’s disease(AD)is a neurodevelopmental impairment that results in a person’s behavior,thinking,and memory loss.Themost common symptoms ofADare losingmemory and early aging.In addition to these,there are several serious impacts ofAD.However,the impact ofADcanbemitigatedby early-stagedetection though it cannot be cured permanently.Early-stage detection is the most challenging task for controlling and mitigating the impact of AD.The study proposes a predictive model to detect AD in the initial phase based on machine learning and a deep learning approach to address the issue.To build a predictive model,open-source data was collected where five stages of images of AD were available as Cognitive Normal(CN),Early Mild Cognitive Impairment(EMCI),Mild Cognitive Impairment(MCI),Late Mild Cognitive Impairment(LMCI),and AD.Every stage of AD is considered as a class,and then the dataset was divided into three parts binary class,three class,and five class.In this research,we applied different preprocessing steps with augmentation techniques to efficiently identifyAD.It integrates a random oversampling technique to handle the imbalance problem from target classes,mitigating the model overfitting and biases.Then three machine learning classifiers,such as random forest(RF),K-Nearest neighbor(KNN),and support vector machine(SVM),and two deep learning methods,such as convolutional neuronal network(CNN)and artificial neural network(ANN)were applied on these datasets.After analyzing the performance of the used models and the datasets,it is found that CNN with binary class outperformed 88.20%accuracy.The result of the study indicates that the model is highly potential to detect AD in the initial phase.

Design of Online Vision Detection System for Stator Winding Coil

The quality of the stator winding coil directly affects the performance of the motor.A dual-camera online machine vision detection method to detect whether the coil leads and winding regions were qualified was designed.A vision detection platform was designed to capture individual winding images,and an image processing algorithm was used for image pre-processing,template matching and positioning of the coil lead area to set up a coordinate system.After eliminating image noise by Blob analysis,the improved Canny algorithm was used to detect the location of the coil lead paint stripped region,and the time was reduced by about half compared to the Canny algorithm.The coil winding region was trained with the ShuffleNet V2-YOLOv5s model for the dataset,and the detect file was converted to the Open Neural Network Exchange(ONNX)model for the detection of winding cross features with an average accuracy of 99.0%.The software interface of the detection system was designed to perform qualified discrimination tests on the workpieces,and the detection data were recorded and statistically analyzed.The results showed that the stator winding coil qualified discrimination accuracy reached 96.2%,and the average detection time of a single workpiece was about 300 ms,while YOLOv5s took less than 30 ms.

Utility of Droplet Digital PCR Assay for Quantitative Detection of Norovirus in Shellfish, from Production to Consumption in Guangxi, China

Objective Shellfish are recognized as important vehicles of norovirus-associated gastroenteritis. The present study aimed to monitor norovirus contamination in oysters along the farm-to-fork continuum in Guangxi, a major oyster production area in Southwestern China. Methods Oyster samples were collected monthly from farms, markets, and restaurants, from January to December 2016. Norovirus was detected and quantified by one-step reverse transcription-droplet digital polymerase chain reaction（RT-ddPCR）. Results A total of 480 oyster samples were collected and tested for norovirus genogroups I and II. Norovirus was detected in 20.7% of samples, with genogroup II predominating. No significant difference was observed in norovirus prevalence among different sampling sites. The norovirus levels varied widely, with a geometric mean of 19,300 copies/g in digestive glands. Both norovirus prevalence and viral loads showed obvious seasonality, with a strong winter bias. Conclusion This study provides a systematic analysis of norovirus contamination ‘from the farm to the fork＇ in Guangxi. RT-ddPCR can be a useful tool for detection and quantification of low amounts of norovirus in the presence of inhibitors found particularly in foodstuffs. This approach will contribute to the development of strategies for controlling and reducing the risk of human illness resulting from shellfish consumption.

Application of droplet digital PCR in detection of seed-transmitted pathogen Acidovorax citrulli

Bacterial fruit blotch caused by Acidovorax citrulli is a serious threat to cucurbit industry worldwide.The pathogen is seedtransmitted,so seed detection to prevent distribution of contaminated seed is crucial in disease management.In this study,we adapted a quantitative real-time PCR(qPCR)assay to droplet digital PCR(ddPCR)format for A.citrulli detection by optimizing reaction conditions.The performance of ddPCR in detecting A.citrulli pure culture,DNA,infested watermelon/melon seed and commercial seed samples were compared with multiplex PCR,qPCR,and dilution plating method.The lowest concentrations detected(LCD)by ddPCR reached up to 2 fg DNA,and 102 CFU mL–1 bacterial cells,which were ten times more sensitive than those of the qPCR.When testing artificially infested watermelon and melon seed,0.1%infestation level was detectable using ddPCR and dilution plating method.The 26 positive samples were identified in 201 commercial seed samples through ddPCR,which was the highest positive number among all the methods.High detection sensitivity achieved by ddPCR demonstrated a promising technique for improving seed-transmitted pathogen detection threshold in the future.

Development and Evaluation of an Optical Sensing System for Detection of Herbicide Spray Droplets

Real time monitoring of herbicide spray droplet drift is important for crop production management and environmental protection. Existing spray droplet drift detection methods, such as water-sensitive paper and tracers of fluorescence and Rubidium chloride, are time-consuming and laborious, and the accuracies are not high in general. Also, the tracer methods indirectly quantify the spray deposition from the concentration of the tracer and may change the drift characteristics of the sprayed herbicides. In this study, a new optical sensor system was developed to directly detect the spray droplets without the need to add any tracer in the spray liquid. The system was prototyped using a single broadband programmable LED light source and a near infrared sensor containing 6 broadband spectral detectors at 610, 680, 730, 760, 810, and 860 nm to build a detection system for monitoring and analysis of herbicide spray droplet drift. A rotatory structure driven by a stepper motor in the system was created to shift the droplet capture line going under the optical sensor to measure and collect the spectral signals that reflect spray drift droplets along the line. The system prototype was tested for detection of small (Very Fine and Fine), medium (Medium), and large (Coarse) droplets within the droplet classifications of the American Society of Agricultural and Biological Engineers. Laboratory testing results indicated that the system could detect the droplets of different sizes and determine the droplet positions on the droplet capture line with 100% accuracy at the wavelength of 610 nm selected from the 6 bands to detect the droplets.

基于改进YOLOX-S的轻量化煤矸石检测方法研究

目的 为了探索基于现有机器视觉煤矸石检测方法的模型参数量、计算量对检测速度和嵌入式设备的影响,方法 提出一种基于改进的无锚框YOLOX-S轻量化煤矸石检测模型。为使模型能提取更真实的煤矸石特征信息,收集分选现场煤矸石样本,保证实际环境下的煤矸石检测效果,适应实际生产环境。结合CSPNet,将输入的特征图分割成两个分支,实现更丰富的梯度组合,同时减少模型计算量;之后在其中一条分支使用Ghost轻量化卷积,通过少量常规卷积生成一组特征图,达到初次减少计算量和参数量的效果,然后在此特征图基础上经过简单线性变化操作,生成一组新的特征图,将两组特征图进行融合,降低对计算资源需求的同时,也达到了常规卷积相同的特征提取效果;引入LeakyReLU激活函数减弱模型梯度消失的影响,提取更深更多的特征信息;最后融合两个分支特征,保证较高的检测精度,提升模型检测速度。采用CIOU Loss(complete IOU loss)优化目标边界框回归损失函数,使模型回归损失收敛更快,提高模型目标定位能力。结果 与原模型相比,本文改进模型在保证较高的平均精度均值90.51%情况下,模型参数减少47%,计算量减少49%,检测速度达到50帧/s。结论 轻量化煤矸石检测模型使智能化煤矸石检测在实际生产环境中具有一定的应用前景。

S-Detect在乳腺肿块诊断中出现假阴性和假阳性的影响因素

目的:研究S-Detect技术在乳腺肿块诊断中出现假阳性和假阴性结果的影响因素。方法:回顾并分析2019年5月—2022年3月南京医科大学第一附属医院613例女性患者的697个乳腺病灶,患者均进行了常规超声检查和S-Detect检查并取得手术后病理学检查结果。以病理学检查结果为标准,绘制受试者工作特征(receiver operating characteristic,ROC)曲线评估S-Detect诊断效能。将患者年龄、肿块最大径、形状、边缘、生长方向、钙化情况、后方回声、血流分级纳入分析,采用t检验或Mann-Whitney U检验比较假阴性与真阴性组、假阳性与真阳性组的连续变量,采用χ^(2)检验或Fisher精确概率检验比较分类变量,采用多因素二元logistic回归法分析独立影响因素。结果:患者的平均年龄为(47.1±13.6)岁,697个病灶中,良性病灶350个,恶性病灶347个,S-Detect诊断曲线下面积(area under curve,AUC)为0.835,Kappa值为0.670。患者年龄≥45岁(OR=2.898,P=0.002)、肿块边缘不光整(OR=4.778,P<0.001)、血流分级为2或3级(OR=2.447,P=0.009)与假阴性结果相关。患者年龄<45岁(OR=9.735,P<0.001)、肿块最大径<20 mm(OR=2.480,P=0.015)、肿块形状规则(OR=4.097,P=0.003)、边缘光整(OR=8.175,P<0.001)、血流分级为0或1级(OR=3.351,P=0.001)与假阳性结果显著相关。结论:当S-Detect诊断结果为良性时,患者年龄较大、肿块边缘不光整、血流分级较高是出现假阴性的影响因素。当S-Detect诊断结果为恶性时,患者较年轻、肿块较小、形状规则、边缘光整、血流分级较低是出现假阳性的影响因素。

基于1DCNN和D-S多信息融合的光伏系统直流母线串联电弧故障检测

直流母线是光伏系统输出能源的主干道,由于长期曝晒、风化等作用,电缆、连接器等组件劣化,光伏系统直流母线中发生电弧的可能性急剧上升,极易引发火灾、触电等事故。在光伏系统中,串联电弧故障将使回路电流下降,传统的过流保护无法识别。因此,本文提出基于深度学习和证据理论(D-S)的方法来识别串联电弧故障,该方法基于并联电容器电流和电压信号,采用一维卷积神经网络(1DCNN)对检测数据进行电弧识别;在此基础上将基于单个传感数据的识别结果作为证据,运用D-S多信息合成法则计算得到信度分配,最后利用决策规则判断是否发生串联电弧故障。搭建多参数可调模型获取数据进行测试,结果表明:使用1DCNN识别方法,基于并联电容器电流和电压信号的串联电弧识别准确率分别为97.19%和94.98%,而基于1DCNN和D-S多信息融合的光伏系统直流串联电弧故障检测的识别准确率可提升至99%以上。

不同超声成像参数对S-Detect技术用于乳腺结节良恶性鉴别诊断中的影响

目的探讨超声成像参数对S-Detect技术诊断结果产生的影响。方法前瞻性收集2021年10月至2022年3月因乳腺结节在浙江大学医学院附属邵逸夫医院就诊的患者,共纳入133例患者(143个结节)。设置5种超声成像参数条件,包括基准(单焦点、焦点位于病灶中部水平、病灶深度适合)、双焦点、焦点位置过浅、焦点位置过深、扫查深度过深。分别存储在不同超声成像参数下获得的超声图像,并应用S-Detect技术对图像进行分析解读。比较基准参数设置与其他参数设置之间的诊断结果一致性及超声特征判读的一致性。并以病理结果为“金标准”,比较各个参数设置条件下的诊断效能。结果扫查深度过深与基准条件的诊断一致性(kappa=0.771)较其他设置更低,对于形状(kappa=0.489)及内部回声(kappa=0.442)这两个超声特征判读的一致性也较其他设置低。同时诊断效能(AUC=0.716)为各个设置中的最低者,且与基准设置的诊断效能差距最大。其他各项参数条件与基准条件的一致性较好,诊断效能与基准条件之间无显著性差异。结论对比基准参数设置,在不同成像参数设置中,扫查深度过深条件下的诊断一致性、超声特征判读一致性、诊断效能均较其他条件更低。因此应用S-Detect技术时应避免采用过深的扫查深度。

经验小波变换和改进S变换结合的电能质量检测与识别方法

为分析不确定干扰因素影响下的实际电力网络电能质量问题,提出一种经验小波变换(EWT)和改进S变换相结合的电能质量检测与识别方法。该方法一方面利用EWT联合归一化直接正交(NDQ)算法和奇异值分解(SVD)算法准确提取调幅-调频分量的频率、幅值和时间参数,另一方面考虑到EWT算法在高噪声环境下瞬时幅值波动的问题,引入改进S变换提取高噪声干扰下的电能质量扰动时频信息,最后,基于EWT和改进S变换提取的扰动特征向量,利用基于改进粒子群优化算法(IPSO)优化支持向量机(SVM)的电能质量扰动识别分类器实现扰动类型的精确识别。仿真和实验表明所提方法在复合扰动识别分类时平均识别准确率为93.23%,且能够准确识别4种实测扰动信号。

改进YOLOX-s的密集垃圾检测方法

针对密集堆放的多种类垃圾检测存在识别率低、定位不够准确和待测目标被误检、漏检问题,提出了一种融合多头自注意力机制改进YOLOX-s的垃圾检测方法。在特征提取网络嵌入SwinTransformer模块,引入基于滑窗操作的多头自注意力机制,使得网络兼顾全局特征信息和重点特征信息,减少误检现象;在预测输出网络中使用可变形卷积,对初始预测框进行精细化处理,提高定位精度;在EIoU损失的基础上引入加权系数,提出加权IoU-EIoU损失,自适应调整训练时不同阶段不同损失的关注程度,进一步加快训练网络的收敛速度。在公开204类垃圾检测数据集中进行测试,结果表明,所提改进算法的平均精度均值分别可达80.5%和92.5%,优于当前流行目标检测算法,且检测速度快,满足实时性需求。

Droplet microfluidic chip for precise monitoring of dynamic solution changes

In this work,an automated microfluidic chip that uses negative pressure to sample and analyze solutions with high temporal resolution was developed.The chip has a T-shaped channel for mixing the sample with a fluorescent indicator,a flow-focusing channel for generating droplets in oil,and a long storage channel for incubating and detecting the droplets.By monitoring the fluorescence intensity of the droplets,the device could detect changes in solution accurately over time.The chip can generate droplets at frequencies of up to 42 Hz with a mixing ratio of 1:1 and a temporal resolution of 3–6 s.It had excellent linearity in detecting fluorescein solution in the concentration range 1–5μM.This droplet microfluidic chip provides several advantages over traditional methods,including high temporal resolution,stable droplet generation,and faster flow rates.This approach could be applied to monitoring calcium ions with a dynamic range from 102 to 107 nM and a detection limit of 10 nM.

Range anomaly suppression based on neighborhood pixels detection in ladar range images

Research on the range anomaly suppression algorithm in laser radar （ladar） range images is significant in the application and development of ladar. But most of existing algorithms cannot protect the edge and linear target well while suppressing the range anomaly. Aiming at this problem, the differences among the edge, linear target, and range anomaly are analyzed and a novel algo- rithm based on neighborhood pixels detection is proposed. Firstly, the range differences between current pixel and its neighborhood pixels are calculated. Then, the number of neighborhood pixels is detected by the range difference threshold. Finally, whether the current pixel is a range anomaly is distinguished by the neighbor- hood pixel number threshold. Experimental results show that the new algorithm not only has a better range anomaly suppression performance and higher efficiency, but also protects the edge and linear target preferably compared with other algorithms.