Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Target tracking method of Siamese networks based on the broad learning system

Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time tracking.Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time performance.However,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during tracking.Therefore,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online.The broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning ability.Aiming at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is proposed.The method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐detection.The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the adaptability.Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

基于GA-BLS方法的手势识别研究

为进一步提升人机交互领域中手势识别的精度和速度,探究肌肉疲劳对手势识别的影响规律,提出了改进的GA-BLS方法,利用遗传算法(genetic algorithms,GA)优化宽度学习(broad learning system,BLS)模型参数,并使用弹性网络回归改进传统的BLS模型。利用所提模型对8种手势下的A型超声信号和肌电信号进行手势识别分析,并与SVM、KNN、RF、LDA等方法进行对比,以验证所研究方法的有效性;将长时间段下的A型超声信号和肌电信号切分成4个数据段,发现随着肌肉疲劳程度的增加,手势识别的准确率均呈现出明显下降的趋势,而且A型超声信号相较于肌电信号具有更好的抗疲劳特性。

A Broad Learning-Driven Network Traffic Analysis System Based on Fog Computing Paradigm

The development of communication technologies which support traffic-intensive applications presents new challenges in designing a real-time traffic analysis architecture and an accurate method that suitable for a wide variety of traffic types.Current traffic analysis methods are executed on the cloud,which needs to upload the traffic data.Fog computing is a more promising way to save bandwidth resources by offloading these tasks to the fog nodes.However,traffic analysis models based on traditional machine learning need to retrain all traffic data when updating the trained model,which are not suitable for fog computing due to the poor computing power.In this study,we design a novel fog computing based traffic analysis system using broad learning.For one thing,fog computing can provide a distributed architecture for saving the bandwidth resources.For another,we use the broad learning to incrementally train the traffic data,which is more suitable for fog computing because it can support incremental updates of models without retraining all data.We implement our system on the Raspberry Pi,and experimental results show that we have a 98%probability to accurately identify these traffic data.Moreover,our method has a faster training speed compared with Convolutional Neural Network(CNN).

A broad learning-based comprehensive defence against SSDP reflection attacks in IoTs

The proliferation of Internet of Things(IoT)rapidly increases the possiblities of Simple Service Discovery Protocol(SSDP)reflection attacks.Most DDoS attack defence strategies deploy only to a certain type of devices in the attack chain,and need to detect attacks in advance,and the detection of DDoS attacks often uses heavy algorithms consuming lots of computing resources.This paper proposes a comprehensive DDoS attack defence approach which combines broad learning and a set of defence strategies against SSDP attacks,called Broad Learning based Comprehensive Defence(BLCD).The defence strategies work along the attack chain,starting from attack sources to victims.It defends against attacks without detecting attacks or identifying the roles of IoT devices in SSDP reflection attacks.BLCD also detects suspicious traffic at bots,service providers and victims by using broad learning,and the detection results are used as the basis for automatically deploying defence strategies which can significantly reduce DDoS packets.For evaluations,we thoroughly analyze attack traffic when deploying BLCD to different defence locations.Experiments show that BLCD can reduce the number of packets received at the victim to 39 without affecting the standard SSDP service,and detect malicious packets with an accuracy of 99.99%.

Music Emotion Recognition Based on Feature Fusion Broad Learning Method

With the rapid development in the field of artificial intelligence and natural language processing(NLP),research on music retrieval has gained importance.Music messages express emotional signals.The emotional classification of music can help in conveniently organizing and retrieving music.It is also the premise of using music for psychological intervention and physiological adjustment.A new chord-to-vector method was proposed,which converted the chord information of music into a chord vector of music and combined the weight of the Mel-frequency cepstral coefficient(MFCC) and residual phase(RP) with the feature fusion of a cochleogram.The music emotion recognition and classification training was carried out using the fusion of a convolution neural network and bidirectional long short-term memory(BiLSTM).In addition,based on the self-collected dataset,a comparison of the proposed model with other model structures was performed.The results show that the proposed method achieved a higher recognition accuracy compared with other models.

LSTM-WBLS模型在日降水量预测中的应用

基于长短时记忆网络(Long Short-Term Memory, LSTM)降水量预测模型存在过拟合、时滞现象,而宽度学习系统(Broad Learning System, BLS)无需多次迭代的特点有助于解决LSTM的上述缺点.加权宽度学习系统(Weighted Broad Learning System, WBLS)通过在BLS中引入加权惩罚因子约束分配样本权重,降低噪声和异常值对降水量预测精度的影响.本文提出一种LSTM-WBLS日降水量预测模型,选取湖北省巴东站日降水量进行实证研究,并考虑气压、气温、湿度、风速和日照等因素对降水量的影响.实验结果表明,与现有的预测模型相比,LSTM-BLS模型在RMSE、MAE和R^(2)等评价指标上均有显著提升.不同时间步长下,本文模型预测精度均优于现有模型,验证了其稳定性.与LSTM相比,WBLS直接计算权重的特点使得LSTM-WBLS的运算效率并未降低.

基于GRU-BLS的超短期光伏发电功率预测

光伏发电功率的准确预测对电网的稳定运行具有重要的意义。针对深度学习训练耗时长和宽度学习特征提取能力弱等问题,将门控循环单元(GRU)与宽度学习系统(BLS)相融合,提出了用于超短期光伏发电功率预测的GRU-BLS模型。先使用GRU训练序列样本,再将所学习到的隐特征作为新的输入特征,最后在BLS中构造特征节点和增强节点以形成最终的特征。所建立的模型在保留深度学习高预测精度的前提下,有效地缩短了模型的训练时间。在实际的光伏发电数据集上进行实验,评估所提模型在不同季节和天气类型下的性能。实验结果表明:与长短期记忆(LSTM),GRU,BLS和LSTM-BLS等模型相比,GRU-BLS的RMSE值降低了23.89%~75.68%,且TIC值和MAPE值也得到了显著改善。

A Federated Bidirectional Connection Broad Learning Scheme for Secure Data Sharing in Internet of Vehicles

Data sharing in Internet of Vehicles(IoV)makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems(ITS).As IoV is a multi-user mobile scenario,the reliability and efficiency of data sharing need to be further enhanced.Federated learning allows the server to exchange parameters without obtaining private data from clients so that the privacy is protected.Broad learning system is a novel artificial intelligence technology that can improve training efficiency of data set.Thus,we propose a federated bidirectional connection broad learning scheme(FeBBLS)to solve the data sharing issues.Firstly,we adopt the bidirectional connection broad learning system(BiBLS)model to train data set in vehicular nodes.The server aggregates the collected parameters of BiBLS from vehicular nodes through the federated broad learning system(FedBLS)algorithm.Moreover,we propose a clustering FedBLS algorithm to offload the data sharing into clusters for improving the aggregation capability of the model.Some simulation results show our scheme can improve the efficiency and prediction accuracy of data sharing and protect the privacy of data sharing.

基于AW-BLS的电力系统暂态稳定评估

为有效降低电力系统运行数据中样本不平衡问题对基于机器学习的暂态稳定评估方法分类性能的影响,提出一种基于自适应权重宽度学习系统AW-BLS(adaptive weighted-broad learning system)的电力系统暂态稳定评估方法。首先,在BLS的宽度结构中引入权重因子以改进BLS模型,有效降低了两类样本数量差距对学习过程的影响。然后,利用电力系统故障前的稳态运行数据对AW-BLS模型进行训练。最后,通过算例分析表明,所提方法在数据集存在样本不平衡问题时具有良好的评估准确率,同时还拥有较好的泛化能力。

基于双向门控式宽度学习系统的监测数据结构变形预测

监测数据深度学习预测模型运算量大、实时性差,为此结合宽度学习系统(BLS)和双向长短时记忆(Bi-LSTM)模型的优势,提出基于双向门控式宽度学习系统(Bi-G-BLS)的结构变形预测模型.对BLS的特征节点增加循环反馈和遗忘门结构,提高当前节点对前一节点的依赖关系,分别从正向和反向提取时间序列的内部特征,充分挖掘数据的双向特征,在提高模型预测精确度的同时减少模型预测时间.基于实测的地铁基坑沉降监测数据的测试结果显示,所提预测模型与门控循环单元(GRU)、BLS、Bi-LSTM、G-BLS模型相比,均方根误差(RMSE)、平均绝对误差(MAE)、平均绝对百分比误差(MAPE)平均分别降低了21.04%、12.81%、24.41%;在预测精度相近的情况下,所提模型的预测时间比Bi-LSTM模型降低了99.59%.结果表明,所提模型在预测速度和精确度上较对比模型有明显提升.

结合矩阵补全的宽度协同过滤推荐算法

协同过滤是推荐系统中最经典的方法之一,能够满足人们对个性化推荐任务的需求,但许多协同过滤算法在面对评分数据稀疏性问题时推荐效果不佳。为解决此问题,提出一种结合矩阵补全的宽度协同过滤推荐算法。先使用矩阵补全技术对用户项目评分矩阵进行补全,再利用补全后的矩阵对已评分的用户和项目分别寻找其近邻项,进而构造用户与项目的评分协同向量,最后使用宽度学习系统来构建用户项目与评分之间的复杂的非线性关系。在MovieLens和filmtrust数据集上对所提出算法的有效性进行检验。试验结果表明,与当前最先进的方法相比,该方法能够有效地缓解数据稀疏性问题,具有较低的计算复杂度,在一定程度上提升了推荐系统的性能。

宽度-深度融合时频分析的径流智能预测方法

为解决现有基于LSTM的径流预测模型易陷入局部最优的问题,提出了基于VMD-LSTMBLS(variational mode decomposition-LSTM-broad learning system)的径流预测模型。将宽度学习系统与LSTM结合,针对径流序列多噪音特点,采用时频分析方法中的变分模态分解,将径流时间序列的一维时域信号变换到二维时频平面,减少噪声对预测结果的影响。仿真结果表明:与基线模型及现有基于LSTM的径流预测模型相比,该模型的预测精度有较为明显的提高。

先立其大,易简工夫,道不外索——论陆九渊的学习价值观

陆九渊的学习概念是广义的,涵盖求学、治学及借以成人等。通过对天人、义利和理欲关系的辨析,确立“人与宇宙相统一”“志乎义”和“从大体”的价值取向,进而对“学”的发端、动机和功能等进行规定。基于“先立其大”“易简工夫”和“道不外索”三项“学”的价值规范,提出学习应先立其大而不应立卑小志向和目标,应易简工夫而不应支离事业,应道不外索而不应向外求知真理,进一步明确应怎样学而不应怎样学的问题。以“成人”和“行道”的价值理想体现“学”的最高价值追求。陆九渊的学习价值观给我们的启示是学习的目的、内容和方法有主次本末之分,应以德为先;学习须先立志,应志存高远;学习应整体明悟,不能拘泥于细枝末节;学习应独立思考,不能迷信书本教条;学习应躬行实践,不能埋没于文义。

基于BLS的无刷发电机旋转整流器特征提取技术研究

研究一种基于宽度学习系统(broadlearningsystem,BLS)的特征自适应提取方法,并将其应用于航空发电机旋转整流器二极管故障分类问题。针对目前宽度学习系统中参数选择等问题,尝试将网格搜索法与宽度学习系统进行结合,提出一种改进的宽度学习系统,该方法可以自适应的计算网络结构,并进行故障特征提取。通过建立的航空发电机仿真模型和实际民用发电机平台的诊断实验表明,BLS与现有的一些典型故障诊断方法相比,在诊断性能相近的情况下,还具有较高的诊断速度。

基于数据驱动的无人机集群故障检测与诊断

无人机集群系统对安全性和稳定性要求极高,实时的故障检测与诊断技术是保证安全可靠运行的有力手段。提出一种基于统计模型和改进宽度学习(BLS)模型的故障诊断方法。所提方法通过多元数据统计分析表征无人机集群系统在正常与不同故障模式下的行为特征,采用改进的BLS模型实现准确、快速的故障诊断。在此基础上,开发无人机集群系统的高逼真可视化仿真验证平台对所提方法的合理性与有效性进行验证。实验结果表明,所提方法与目前主流方法相比具有明显的诊断优势。

分时电价下任务调度–人员排班组合问题的代理模型求解研究

在分时电价背景下,制造成本和人力成本往往难以取得平衡:晚上电价较低但人员加班费较高,白天人员时薪较低而电价却较高。若将两个问题联合建模,则规模较大,不易求解。在实际应用中,较多采用先进行任务调度,再对人员排班的分阶段建模求解方法,但该求解思路难以保证得到较低成本的解。针对这一问题,提出一种代理模型的方法,以GA算法生成两个子问题的多组较优可行解作为训练样本,利用BP神经网络、深度学习及宽度学习系统分别拟合组合问题的代理模型,并采用BFGS法寻优。随着工件与工序数目的增加,本文所提供的自适应采样算法能有效解决维数灾问题。算例结果表明,新方法能得到明显优于利用遗传算法分阶段求解得到的结果,能为企业节省高达11.91%的电费与人力总成本。

基于宽度网络架构的单模型主导联邦学习

联邦学习是一种分布式机器学习方法,它将数据保留在本地,仅将计算结果上传到客户端,从而提高了模型传递与聚合的效率和安全性.然而,联邦学习面临的一个重要挑战是,上传的模型大小日益增加,大量参数多次迭代,给通信能力不足的小型设备带来了困难.因此在本文中,客户端和服务器被设置为仅一次的互相通信机会.联邦学习中的另一个挑战是,客户端之间的数据规模并不相同.在不平衡数据场景下,服务器的模型聚合将变得低效.为了解决这些问题,本文提出了一个仅需一轮通信的轻量级联邦学习框架,在联邦宽度学习中设计了一种聚合策略算法,即FBL-LD.算法在单轮通信中收集可靠的模型并选出主导模型,通过验证集合理地调整其他模型的参与权重来泛化联邦模型.FBL-LD利用有限的通信资源保持了高效的聚合.实验结果表明,FBL-LD相比同类联邦宽度学习算法具有更小的开销和更高的精度,并且对不平衡数据问题具有鲁棒性.

融合 OCEEMDAN的多模态互量纲一化与宽度学习改进的智能故障诊断

滚动轴承作为旋转机械的重要组成部分,在恶劣环境运行导致振动信号具有非线性和非平稳的特点,使得区分故障信号和正常信号变得困难。针对此,提出一种结合多模态互量纲一化(MMDI)与宽度学习系统(BLS)的智能故障诊断方法。通过优化完全自适应噪声集合经验模态(OCEEMDAN)与小波阈值对轴承观测信号进行分解处理,对有效的本征模态函数(IMF)重构并提取MDI,构建了一批MMDI;采用反向传播算法(BP)与堆叠模块方式优化BLS,改进的BLS算法能够快速识别不同的故障类型;最后通过凯斯西储大学轴承数据中心与某实验室提供的轴承数据集对所提方法进行验证,平均准确率分别为99.8%与100%,验证了方法的有效性。

Multi-surrogate framework with an adaptive selection mechanism for production optimization

Data-driven surrogate models that assist with efficient evolutionary algorithms to find the optimal development scheme have been widely used to solve reservoir production optimization problems.However,existing research suggests that the effectiveness of a surrogate model can vary depending on the complexity of the design problem.A surrogate model that has demonstrated success in one scenario may not perform as well in others.In the absence of prior knowledge,finding a promising surrogate model that performs well for an unknown reservoir is challenging.Moreover,the optimization process often relies on a single evolutionary algorithm,which can yield varying results across different cases.To address these limitations,this paper introduces a novel approach called the multi-surrogate framework with an adaptive selection mechanism(MSFASM)to tackle production optimization problems.MSFASM consists of two stages.In the first stage,a reduced-dimensional broad learning system(BLS)is used to adaptively select the evolutionary algorithm with the best performance during the current optimization period.In the second stage,the multi-objective algorithm,non-dominated sorting genetic algorithm II(NSGA-II),is used as an optimizer to find a set of Pareto solutions with good performance on multiple surrogate models.A novel optimal point criterion is utilized in this stage to select the Pareto solutions,thereby obtaining the desired development schemes without increasing the computational load of the numerical simulator.The two stages are combined using sequential transfer learning.From the two most important perspectives of an evolutionary algorithm and a surrogate model,the proposed method improves adaptability to optimization problems of various reservoir types.To verify the effectiveness of the proposed method,four 100-dimensional benchmark functions and two reservoir models are tested,and the results are compared with those obtained by six other surrogate-model-based methods.The results demonstrate that our approach can obtain the maximum net present value(NPV)of the target production optimization problems.