An Efficient and Secure Privacy-Preserving Federated Learning Framework Based on Multiplicative Double Privacy Masking

With the increasing awareness of privacy protection and the improvement of relevant laws,federal learning has gradually become a new choice for cross-agency and cross-device machine learning.In order to solve the problems of privacy leakage,high computational overhead and high traffic in some federated learning schemes,this paper proposes amultiplicative double privacymask algorithm which is convenient for homomorphic addition aggregation.The combination of homomorphic encryption and secret sharing ensures that the server cannot compromise user privacy from the private gradient uploaded by the participants.At the same time,the proposed TQRR(Top-Q-Random-R)gradient selection algorithm is used to filter the gradient of encryption and upload efficiently,which reduces the computing overhead of 51.78%and the traffic of 64.87%on the premise of ensuring the accuracy of themodel,whichmakes the framework of privacy protection federated learning lighter to adapt to more miniaturized federated learning terminals.

Masked Autoencoders as Single Object Tracking Learners

Significant advancements have beenwitnessed in visual tracking applications leveragingViT in recent years,mainly due to the formidablemodeling capabilities of Vision Transformer(ViT).However,the strong performance of such trackers heavily relies on ViT models pretrained for long periods,limitingmore flexible model designs for tracking tasks.To address this issue,we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders,called TrackMAE.During pretraining,we employ two shared-parameter ViTs,serving as the appearance encoder and motion encoder,respectively.The appearance encoder encodes randomly masked image data,while the motion encoder encodes randomly masked pairs of video frames.Subsequently,an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel level.In this way,ViT learns to understand both the appearance of images and the motion between video frames simultaneously.Experimental results demonstrate that ViT-Base and ViT-Large models,pretrained with TrackMAE and combined with a simple tracking head,achieve state-of-the-art(SOTA)performance without additional design.Moreover,compared to the currently popular MAE pretraining methods,TrackMAE consumes only 1/5 of the training time,which will facilitate the customization of diverse models for tracking.For instance,we additionally customize a lightweight ViT-XS,which achieves SOTA efficient tracking performance.

Deep reinforcement learning based multi-level dynamic reconfiguration for urban distribution network:a cloud-edge collaboration architecture

With the construction of the power Internet of Things(IoT),communication between smart devices in urban distribution networks has been gradually moving towards high speed,high compatibility,and low latency,which provides reliable support for reconfiguration optimization in urban distribution networks.Thus,this study proposed a deep reinforcement learning based multi-level dynamic reconfiguration method for urban distribution networks in a cloud-edge collaboration architecture to obtain a real-time optimal multi-level dynamic reconfiguration solution.First,the multi-level dynamic reconfiguration method was discussed,which included feeder-,transformer-,and substation-levels.Subsequently,the multi-agent system was combined with the cloud-edge collaboration architecture to build a deep reinforcement learning model for multi-level dynamic reconfiguration in an urban distribution network.The cloud-edge collaboration architecture can effectively support the multi-agent system to conduct“centralized training and decentralized execution”operation modes and improve the learning efficiency of the model.Thereafter,for a multi-agent system,this study adopted a combination of offline and online learning to endow the model with the ability to realize automatic optimization and updation of the strategy.In the offline learning phase,a Q-learning-based multi-agent conservative Q-learning(MACQL)algorithm was proposed to stabilize the learning results and reduce the risk of the next online learning phase.In the online learning phase,a multi-agent deep deterministic policy gradient(MADDPG)algorithm based on policy gradients was proposed to explore the action space and update the experience pool.Finally,the effectiveness of the proposed method was verified through a simulation analysis of a real-world 445-node system.

An Automated Real-Time Face Mask Detection System Using Transfer Learning with Faster-RCNN in the Era of the COVID-19 Pandemic

Today,due to the pandemic of COVID-19 the entire world is facing a serious health crisis.According to the World Health Organization(WHO),people in public places should wear a face mask to control the rapid transmission of COVID-19.The governmental bodies of different countries imposed that wearing a face mask is compulsory in public places.Therefore,it is very difficult to manually monitor people in overcrowded areas.This research focuses on providing a solution to enforce one of the important preventative measures of COVID-19 in public places,by presenting an automated system that automatically localizes masked and unmasked human faces within an image or video of an area which assist in this outbreak of COVID-19.This paper demonstrates a transfer learning approach with the Faster-RCNN model to detect faces that are masked or unmasked.The proposed framework is built by fine-tuning the state-of-the-art deep learning model,Faster-RCNN,and has been validated on a publicly available dataset named Face Mask Dataset(FMD)and achieving the highest average precision(AP)of 81%and highest average Recall(AR)of 84%.This shows the strong robustness and capabilities of the Faster-RCNN model to detect individuals with masked and un-masked faces.Moreover,this work applies to real-time and can be implemented in any public service area.

Deep Learning Based Face Mask Detection in Religious Mass Gathering During COVID-19 Pandemic

Notwithstanding the religious intention of billions of devotees,the religious mass gathering increased major public health concerns since it likely became a huge super spreading event for the severe acute respiratory syndrome coronavirus 2(SARS-CoV-2).Most attendees ignored preventive measures,namely maintaining physical distance,practising hand hygiene,and wearing facemasks.Wearing a face mask in public areas protects people from spreading COVID-19.Artificial intelligence(AI)based on deep learning(DL)and machine learning(ML)could assist in fighting covid-19 in several ways.This study introduces a new deep learning-based Face Mask Detection in Religious Mass Gathering(DLFMD-RMG)technique during the COVID-19 pandemic.The DLFMD-RMG technique focuses mainly on detecting face masks in a religious mass gathering.To accomplish this,the presented DLFMD-RMG technique undergoes two pre-processing levels:Bilateral Filtering(BF)and Contrast Enhancement.For face detection,the DLFMD-RMG technique uses YOLOv5 with a ResNet-50 detector.In addition,the face detection performance can be improved by the seeker optimization algorithm(SOA)for tuning the hyperparameter of the ResNet-50 module,showing the novelty of the work.At last,the faces with and without masks are classified using the Fuzzy Neural Network(FNN)model.The stimulation study of the DLFMD-RMG algorithm is examined on a benchmark dataset.The results highlighted the remarkable performance of the DLFMD-RMG model algorithm in other recent approaches.

基于空间注意力机制的Mask R-CNN致密储层岩石薄片图像鉴定

针对陆相致密储层岩石薄片鉴定识别难、制片成本高、时间消耗长和人为主观强等难题,选取鄂尔多斯盆地临兴区块上古生界和松辽盆地三肇凹陷扶余油层为靶区,提出一种基于深度学习的致密油储层岩石薄片人工智能鉴定方法,引入图像预处理技术去除岩石薄片图像噪声并统一图像像素大小,构建空间几何增广机制,基于空间注意力机制改进Mask R-CNN算法,并将上述方法应用于实例靶区进行有效性验证。结果表明:图像预处理技术能够在保障图像特征的前提下,有效提高图像质量,减少噪声干扰;空间几何图像增广机制能够在在一定程度上增加可用样本的数量;基于空间注意力机制的Mask R-CNN算法可以同时完成复杂岩石薄片成分的分割与智能识别工作,分割精度在不同数据集情况下的平均精度为89.2%,整体识别准确率为93%,适用于致密油储层岩石薄片特征鉴定。

基于改进Mask R-CNN的青菜杂质检测研究

绿叶蔬菜的智能包装加工是实现绿叶蔬菜智能化生产、降低生产成本的重要部分,对绿叶蔬菜在包装加工时的杂质检测是其重要前提。以青菜为研究对象,提出一种基于Mask R-CNN的青菜杂质检测模型。首先采集标注掺杂枯树叶、枯菜叶和碎纸片3种常见杂质的青菜图像1370多张,并通过数据增强的方法扩充建立含有2740张青菜杂质图像的数据集。为减少背景对杂质检测的影响,通过在Mask R-CNN模型中加入协调注意力机制,同时添加全连接层和Dropout层,增强模型特征提取能力,减少过拟合现象,并使用迁移学习方法对模型进行微调。结果表明改进后的Mask R-CNN算法对青菜杂质识别的平均精度均值为99.19%,检测速度为8.45 FPS,检测效果良好,可以满足青菜杂质的检测需求。

Detecting While Accessing:A Semi-Supervised Learning-Based Approach for Malicious Traffic Detection in Internet of Things

In the upcoming large-scale Internet of Things(Io T),it is increasingly challenging to defend against malicious traffic,due to the heterogeneity of Io T devices and the diversity of Io T communication protocols.In this paper,we propose a semi-supervised learning-based approach to detect malicious traffic at the access side.It overcomes the resource-bottleneck problem of traditional malicious traffic defenders which are deployed at the victim side,and also is free of labeled traffic data in model training.Specifically,we design a coarse-grained behavior model of Io T devices by self-supervised learning with unlabeled traffic data.Then,we fine-tune this model to improve its accuracy in malicious traffic detection by adopting a transfer learning method using a small amount of labeled data.Experimental results show that our method can achieve the accuracy of 99.52%and the F1-score of 99.52%with only 1%of the labeled training data based on the CICDDoS2019 dataset.Moreover,our method outperforms the stateof-the-art supervised learning-based methods in terms of accuracy,precision,recall and F1-score with 1%of the training data.

Signet Ring Cell Detection from Histological Images Using Deep Learning

Signet Ring Cell(SRC)Carcinoma is among the dangerous types of cancers,and has a major contribution towards the death ratio caused by cancerous diseases.Detection and diagnosis of SRC carcinoma at earlier stages is a challenging,laborious,and costly task.Automatic detection of SRCs in a patient’s body through medical imaging by incorporating computing technologies is a hot topic of research.In the presented framework,we propose a novel approach that performs the identification and segmentation of SRCs in the histological images by using a deep learning(DL)technique named Mask Region-based Convolutional Neural Network(Mask-RCNN).In the first step,the input image is fed to Resnet-101 for feature extraction.The extracted feature maps are conveyed to Region Proposal Network(RPN)for the generation of the region of interest(RoI)proposals as well as they are directly conveyed to RoiAlign.Secondly,RoIAlign combines the feature maps with RoI proposals and generates segmentation masks by using a fully connected(FC)network and performs classification along with Bounding Box(bb)generation by using FC layers.The annotations are developed from ground truth(GT)images to perform experimentation on our developed dataset.Our introduced approach achieves accurate SRC detection with the precision and recall values of 0.901 and 0.897 respectively which can be utilized in clinical trials.We aim to release the employed database soon to assist the improvement in the SRC recognition research area.

A Deep Learning-Based Approach for Road Surface Damage Detection

Timely detection and elimination of damage in areas with excessive vehicle loading can reduce the risk of road accidents.Currently,various methods of photo and video surveillance are used to monitor the condition of the road surface.The manual approach to evaluation and analysis of the received data can take a protracted period of time.Thus,it is necessary to improve the procedures for inspection and assessment of the condition of control objects with the help of computer vision and deep learning techniques.In this paper,we propose a model based on Mask Region-based Convolutional Neural Network(Mask R-CNN)architecture for identifying defects of the road surface in the real-time mode.It shows the process of collecting and the features of the training samples and the deep neural network(DNN)training process,taking into account the specifics of the problems posed.For the software implementation of the proposed architecture,the Python programming language and the TensorFlow framework were utilized.The use of the proposed model is effective even in conditions of a limited amount of source data.Also as a result of experiments,a high degree of repeatability of the results was noted.According to the metrics,Mask R-CNN gave the high detection and segmentation results showing 0.9214,0.9876,0.9571 precision,recall,and F1-score respectively in road damage detection,and Intersection over Union(IoU)-0.3488 and Dice similarity coefficient-0.7381 in segmentation of road damages.

Deep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures

The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades.Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle(UAV)required maximum accuracy.In this paper,we designed a hybrid framework,which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures.The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient(DDPG)to receive the best reward and take actions according to 3D hand gestures input.The UAV consist of a Jetson Nano embedded testbed,Global Positioning System(GPS)sensor module,and Intel depth camera.The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function.The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives(PID)flight controller.There are six reward functions estimated for 2500,5000,7500,and 10000 episodes of training,which have been normalized between 0 to−4000.The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value.The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.

A Deep Learning Model of Traffic Signs in Panoramic Images Detection

To pursue the ideal of a safe high-tech society in a time when traffic accidents are frequent,the traffic signs detection system has become one of the necessary topics in recent years and in the future.The ultimate goal of this research is to identify and classify the types of traffic signs in a panoramic image.To accomplish this goal,the paper proposes a new model for traffic sign detection based on the Convolutional Neural Network for com-prehensive traffic sign classification and Mask Region-based Convolutional Neural Networks(R-CNN)implementation for identifying and extracting signs in panoramic images.Data augmentation and normalization of the images are also applied to assist in classifying better even if old traffic signs are degraded,and considerably minimize the rates of discovering the extra boxes.The proposed model is tested on both the testing dataset and the actual images and gets 94.5%of the correct signs recognition rate,the classification rate of those signs discovered was 99.41%and the rate of false signs was only around 0.11.

Deep Learning-Based Sign Language Recognition for Hearing and Speaking Impaired People

Sign language is mainly utilized in communication with people who have hearing disabilities.Sign language is used to communicate with people hav-ing developmental impairments who have some or no interaction skills.The inter-action via Sign language becomes a fruitful means of communication for hearing and speech impaired persons.A Hand gesture recognition systemfinds helpful for deaf and dumb people by making use of human computer interface(HCI)and convolutional neural networks(CNN)for identifying the static indications of Indian Sign Language(ISL).This study introduces a shark smell optimization with deep learning based automated sign language recognition(SSODL-ASLR)model for hearing and speaking impaired people.The presented SSODL-ASLR technique majorly concentrates on the recognition and classification of sign lan-guage provided by deaf and dumb people.The presented SSODL-ASLR model encompasses a two stage process namely sign language detection and sign lan-guage classification.In thefirst stage,the Mask Region based Convolution Neural Network(Mask RCNN)model is exploited for sign language recognition.Sec-ondly,SSO algorithm with soft margin support vector machine(SM-SVM)model can be utilized for sign language classification.To assure the enhanced classifica-tion performance of the SSODL-ASLR model,a brief set of simulations was car-ried out.The extensive results portrayed the supremacy of the SSODL-ASLR model over other techniques.

基于Mask R-CNN和迁移学习的无人机遥感影像杉木单木树冠提取

【目的】利用无人机遥感影像对树冠进行自动化提取,获取高精度树冠信息。【方法】该研究提出一种基于Mask RCNN和迁移学习的无人机影像单木树冠提取方法。首先,选用在Faster R-CNN基础上改进优化的Mask R-CNN实例分割模型,特征提取网络在ResNet50残差网络和ResNet101残差网络二者间选取最优。其次,引入迁移学习与Mask RCNN一起训练,联合迁移学习的导向作用降低训练时间,提高训练精度。【结果】Mask R-CNN模型的总体精度为93.59%,用户精度为65.46%,F1分数为76.05%,平均精度均值为0.31;载入迁移学习后的Mask R-CNN模型在同等训练条件下比原模型的用户精度提升29.53%,F1分数提升19.63%,平均精度均值提升0.21;分别以ResNet50和ResNet101为特征提取网络的Mask R-CNN模型中,ResNet50+Mask R-CNN模型的总体精度、用户精度、F1分数、平均精度均值各为96.94%、95.57%、96.17%、0.54,ResNet101+Mask R-CNN模型的总体精度、用户精度、F1分数、平均精度均值各为96.20%、94.41%、95.19%、0.49;其中载入迁移学习的ResNet50+Mask R-CNN模型在预测东西冠幅、南北冠幅、树冠面积与样方郁闭度的预测决定系数分别为0.87、0.84、0.93和0.83。【结论】本研究提出的基于Mask R-CNN和迁移学习的方法得到了较为精准的树冠参数结果,为无人机遥感影像评估树木资源提供了一种快速高效的解决方案。

基于Mask R-CNN的复合材料夹杂缺陷自动检测研究

为提高复合材料夹杂缺陷的检测效率,本文提出利用深度学习网络设计一种夹杂缺陷自动检测系统。在图像预处理环节采用两级反锐化掩膜算法突出夹杂缺陷特征,构建复合材料夹杂缺陷图像数据库;采用Mask R-CNN网络模型,经过网络模型训练,得到最优权重参数,最终设计实现缺陷检测软件系统。实验结果表明,Mask R-CNN算法网络准确率达94.6%,召回率达92.4%,AP值达87.3%。该系统应用方便快捷,将有效提高一线人员的缺陷检测效率和检测精度。

基于TD-Mask R-CNN的机械装配体图像实例分割

在机械产品装配过程中,为了准确识别机械装配体零件信息以减少零件漏装、错装等现象,提出一种改进的机械装配体图像实例分割方法TD-Mask R-CNN。首先,在主干网络ResNet101中引入可变形卷积(deformable convolutional networks, DCN)以增加网络模型的泛化能力;其次,使用Transfiner结构作为掩码分支以提高机械零件边缘的分割精度;最后,在Transfiner结构中引入离散余弦变换(discrete cosine transform, DCT)模块以提升模型对机械装配体图像整体的分割能力。实验结果表明,提出的实例分割方法在合成深度图像数据集和真实彩色图像数据集上得到的掩码平均精度(average precision, AP)分别为87.7%和92.0%,与其他主流实例分割算法相比均有所提升。

基于改进Mask R-CNN特征点精确提取技术研究与应用

针对大型零部件自动对接装配系统使用的传统特征提取算法泛化能力不足的问题,提出一种基于改进Mask R-CNN模型的深度学习特征提取算法。首先采集目标对象的图像数据并进行人工标注,采用数据增强策略扩充数据集;其次构建Mask R-CNN模型,基于迁移学习策略预训练模型,使用人工采集数据集训练模型;然后使用鲸鱼优化算法改进Mask R-CNN模型,优化超参数,进一步提升模型性能;最后对传统特征提取算法和基于Mask R-CNN模型的深度学习特征提取算法进行对比实验,验证了在自动对接装配系统中使用所提算法有更高的准确性和更强的泛化能力。

基于视觉技术和Mask R-CNN的法兰盘表面缺陷检测研究

在法兰表面缺陷检测任务中,为了对缺陷进行精准定位和分类,根据缺陷位置和类别综合判定法兰是否符合特定标准的质量要求,结合缺陷特征和相应标准,提出一种基于视觉技术和Mask R-CNN的法兰表面缺陷检测与评估方法。依据法兰的适用原则和缺陷判定标准对法兰表面进行区域划分。通过搭建图像采集平台,采集图像并对其进行预处理操作后添加至网络训练集中。采用Mask R-CNN作为缺陷检测网络的基本框架,结合法兰表面缺陷特点改进Mask R-CNN骨干网络和颈部网络,并对网络性能进行验证。最后,根据检测标准,使用边缘检测算法对模型检测结果进行复检。结果表明:改进后的方法能够实现精确的定位并进行质量评估,满足法兰表面缺陷检测的要求。

基于改进Mask R-CNN模型的宫颈细胞分割

在宫颈细胞分割过程中,原始Mask R-CNN模型采用ResNet50和FPN作为特征提取网络,尽管模型分割效果良好,但仍存在分割速度慢且边缘分割效果欠佳等问题,为此,提出了一种改进Mask R-CNN模型。首先,该模型采用轻量化网络MobileNet V2作为特征提取模块,大幅度降低模型参数量,为图像的实时分割提供了可能。其次,该模型在特征提取网络中融入了注意力模块,通过自适应特征优化功能,最大限度获取底层信息。最后,模型在掩码生成阶段采用跳跃连接的方式,有效融合各尺度信息,提升网络信息获取能力。实验结果表明,改进模型将宫颈细胞核的分割速度提升了50%左右、分割精度提升了7%。

基于SE-Mask-RCNN建筑遗产识别与空间可视化分析

传统建筑是中国宝贵的建筑遗产,承载着优秀的民族建筑文化,是反映城市特色风貌的重要指标。现阶段深度学习识别建筑物的技术相对成熟,但使用街景图片识别建筑遗产并进行地图可视化展示的研究较少,因此,本研究基于Mask-RCNN(mask region-based convolutional neural network)模型,融合SE(squeeze and excitation)注意力机制,提出一种基于SE-Mask-RCNN识别街景图片中建筑遗产的方法。首先,通过路网数据获取百度街景图片,制作数据集。其次,在模型的残差网络(residual network,ResNet)中引入SE注意力机制;并与已有相关方法 U-net(u-shaped network)、全卷积网络(fully convolutional network,FCN)、Mask-RCNN三种模型进行实验对比评价。最后,使用本方法识别研究区域内的街景图片,形成可视化地图,分析建筑遗产在空间上的分布情况。结果表明,本方法可以有效识别城市中的建筑遗产,识别结果较Mask-RCNN、U-Net、FCN模型分别提高了2%、3.1%、4.7%,证明了本方法对城市中建筑遗产的识别具有可靠性和有效性。研究成果可为建筑遗产保护及现状调查提供依据。