基于Stacking融合的LSTM-SA-RBF短期负荷预测

为了解决单个神经网络预测的局限性和时间序列的波动性,提出了一种奇异谱分析(singular spectrum analysis,SSA)和Stacking框架相结合的短期负荷预测方法。利用随机森林筛选出与历史负荷相关性强烈的特征因素,采用SSA为负荷数据降噪,简化模型计算过程;基于Stacking框架,结合长短期记忆(long and short-term memory,LSTM)-自注意力机制(self-attention mechanism,SA)、径向基(radial base functions,RBF)神经网络和线性回归方法集成新的组合模型,同时利用交叉验证方法避免模型过拟合;选取PJM和澳大利亚电力负荷数据集进行验证。仿真结果表明,与其他模型比较,所提模型预测精度高。

基于Stacking集成学习的枣树智能灌溉系统设计与试验

南疆降雨量少,气候干燥,农业用水紧张,水资源节约尤为重要,针对此问题设计一套智能灌溉系统。系统使用阿里云服务器作为上位机,树莓派作为下位机,并搭建相应的操作页面。根据Penman-Monteith公式中需要的气象数据、过去7天需水量以及前1天气象数据为输入向量,作物需水量为输出向量,构建基于随机森林、BP神经网络与岭回归的Stacking集成学习预测模型。结果表明Stacking集成学习预测模型拟合系数R 2为0.973,且MAE、RMSE、MAPE三类误差更小,Stacking集成学习预测模型预测效果更强。灌溉试验中自动灌溉决策正确,系统运行稳定,为新疆地区农业提高水资源利用问题提供思路。

Detection and defending the XSS attack using novel hybrid stacking ensemble learning-based DNN approach

Existing web-based security applications have failed in many situations due to the great intelligence of attackers.Among web applications,Cross-Site Scripting(XSS)is one of the dangerous assaults experienced while modifying an organization's or user's information.To avoid these security challenges,this article proposes a novel,all-encompassing combination of machine learning(NB,SVM,k-NN)and deep learning(RNN,CNN,LSTM)frameworks for detecting and defending against XSS attacks with high accuracy and efficiency.Based on the representation,a novel idea for merging stacking ensemble with web applications,termed“hybrid stacking”,is proposed.In order to implement the aforementioned methods,four distinct datasets,each of which contains both safe and unsafe content,are considered.The hybrid detection method can adaptively identify the attacks from the URL,and the defense mechanism inherits the advantages of URL encoding with dictionary-based mapping to improve prediction accuracy,accelerate the training process,and effectively remove the unsafe JScript/JavaScript keywords from the URL.The simulation results show that the proposed hybrid model is more efficient than the existing detection methods.It produces more than 99.5%accurate XSS attack classification results(accuracy,precision,recall,f1_score,and Receiver Operating Characteristic(ROC))and is highly resistant to XSS attacks.In order to ensure the security of the server's information,the proposed hybrid approach is demonstrated in a real-time environment.

基于F-Stack的高性能ICN网关设计与实现

部署信息中心网络(ICN)协议转换网关是实现ICN与现有IP网络兼容演进的一种方式。为了提升网关在数据流量的处理与转发方面的效率,避免网关的数据处理瓶颈影响ICN提供的性能增益,本文提出一种基于F-Stack开发框架的高性能ICN网关设计方法。该网关系统利用DPDK用户态协议栈快速处理大量TCP连接与流量,并结合DPDK的共享内存与无锁环形队列机制实现进程间通信,不仅具备良好的性能,而且可以降低模块间的耦合性。实验结果表明,在8核CPU资源配置下,本文方法具有良好的性能优势:数据传输速率可达75%网卡线速,同时支持87万个以上的并发连接,且平均处理时延在45μs以下。

基于多模型融合Stacking集成学习的油田产量预测

基于机器学习前沿理论,提出一种基于多模型融合Stacking集成学习方式的组合预测方法,以国内某特高含水油田区块中多口水驱产油井历年生产历史数据为试验样本,预测其动态产油量。依据不同算法的训练原理,选取极限梯度提升树算法、长短记忆网络(LSTM)、时域卷积网络(TCN)等作为模型的基学习器,采用多元线性回归作为模型的元学习器。结果表明:融合后的Stacking模型充分发挥了各基学习器的优势,相比单一模型,融合后的Stacking模型预测平均误差较小,预测鲁棒性较好。该模型的提出对融合模型在特高含水油藏开发方面具有重要的应用意义。

A Dynamic Protocol Stack Structure for Diversified QoS Requirements in Ad Hoc Network

A dynamic protocol stack(DPS) for ad hoc networks, together with a protocol stack construction scheme that is modeled as a multiconstrained knapsack problem is proposed. Compared to the traditional static protocol stack, DPS operates in a dynamic and adaptive manner and is scalable to network condition changes. In addition, a protocol construction algorithm is proposed to dynamically construct of the protocol stack each network node. Simulation results show that, the processing and forwarding performance of our scheme is close to 1 Gb/s, and the performance of our algorithm is close to that of the classical algorithms with much lower complexity.

A Stacking-Based Deep Neural Network Approach for Effective Network Anomaly Detection

An anomaly-based intrusion detection system(A-IDS)provides a critical aspect in a modern computing infrastructure since new types of attacks can be discovered.It prevalently utilizes several machine learning algorithms(ML)for detecting and classifying network traffic.To date,lots of algorithms have been proposed to improve the detection performance of A-IDS,either using individual or ensemble learners.In particular,ensemble learners have shown remarkable performance over individual learners in many applications,including in cybersecurity domain.However,most existing works still suffer from unsatisfactory results due to improper ensemble design.The aim of this study is to emphasize the effectiveness of stacking ensemble-based model for A-IDS,where deep learning(e.g.,deep neural network[DNN])is used as base learner model.The effectiveness of the proposed model and base DNN model are benchmarked empirically in terms of several performance metrics,i.e.,Matthew’s correlation coefficient,accuracy,and false alarm rate.The results indicate that the proposed model is superior to the base DNN model as well as other existing ML algorithms found in the literature.

Self-organization of Reconfigurable Protocol Stack for Networked Control Systems

In networked control systems （NCS）,the control performance depends on not only the control algorithm but also the communication protocol stack.The performance degradation introduced by the heterogeneous and dynamic communication environment has intensified the need for the reconfigurable protocol stack.In this paper,a novel architecture for the reconfigurable protocol stack is proposed,which is a unified specification of the protocol components and service interfaces supporting both static and dynamic reconfiguration for existing industrial communication standards.Within the architecture,a triple-level self-organization structure is designed to manage the dynamic reconfiguration procedure based on information exchanges inside and outside the protocol stack.Especially,the protocol stack can be self-adaptive to various environment and system requirements through the reconfiguration of working mode,routing and scheduling table.Finally,the study on the protocol of dynamic address management is conducted for the system of controller area network （CAN）.The results show the efficiency of our self-organizing architecture for the implementation of a reconfigurable protocol stack.

Iterative learning-based many-objective history matching using deep neural network with stacked autoencoder

This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history matching.The proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering schemes.DNN functions as an inverse model and results in encoded flattened data,while SAE,as a pre-trained neural network,successfully reduces dimensionality and reliably reconstructs geomodels.The iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration step.The proposed workflow shows the small mean absolute percentage error below 4%for all objective functions,while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population uncertainty.Iterative learning-based manyobjective history matching estimates the trends in water cuts that are not reliably included in dynamicdata matching.This confirms the proposed workflow constructs more plausible geo-models.The workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions.

Dynamic prediction of landslide displacement using singular spectrum analysis and stack long short-term memory network

An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models, this paper proposes a dynamic prediction model of landslide displacement based on singular spectrum analysis(SSA) and stack long short-term memory(SLSTM) network. The SSA is used to decompose the landslide accumulated displacement time series data into trend term and periodic term displacement subsequences. A cubic polynomial function is used to predict the trend term displacement subsequence, and the SLSTM neural network is used to predict the periodic term displacement subsequence. At the same time, the Bayesian optimization algorithm is used to determine that the SLSTM network input sequence length is 12 and the number of hidden layer nodes is 18. The SLSTM network is updated by adding predicted values to the training set to achieve dynamic displacement prediction. Finally, the accumulated landslide displacement is obtained by superimposing the predicted value of each displacement subsequence. The proposed model was verified on the Xintan landslide in Hubei Province, China. The results show that when predicting the displacement of the periodic term, the SLSTM network has higher prediction accuracy than the support vector machine(SVM) and auto regressive integrated moving average(ARIMA). The mean relative error(MRE) is reduced by 4.099% and 3.548% respectively, while the root mean square error(RMSE) is reduced by 5.830 mm and 3.854 mm respectively. It is concluded that the SLSTM network model can better simulate the dynamic characteristics of landslides.

Stacked spectral feature space patch: An advanced spectral representation for precise crop classification based on convolutional neural network

Spectral and spatial features in remotely sensed data play an irreplaceable role in classifying crop types for precision agriculture. Despite the thriving establishment of the handcrafted features, designing or selecting such features valid for specific crop types requires prior knowledge and thus remains an open challenge. Convolutional neural networks(CNNs) can effectively overcome this issue with their advanced ability to generate high-level features automatically but are still inadequate in mining spectral features compared to mining spatial features. This study proposed an enhanced spectral feature called Stacked Spectral Feature Space Patch(SSFSP) for CNN-based crop classification. SSFSP is a stack of twodimensional(2 D) gridded spectral feature images that record various crop types’ spatial and intensity distribution characteristics in a 2 D feature space consisting of two spectral bands. SSFSP can be input into2 D-CNNs to support the simultaneous mining of spectral and spatial features, as the spectral features are successfully converted to 2 D images that can be processed by CNN. We tested the performance of SSFSP by using it as the input to seven CNN models and one multilayer perceptron model for crop type classification compared to using conventional spectral features as input. Using high spatial resolution hyperspectral datasets at three sites, the comparative study demonstrated that SSFSP outperforms conventional spectral features regarding classification accuracy, robustness, and training efficiency. The theoretical analysis summarizes three reasons for its excellent performance. First, SSFSP mines the spectral interrelationship with feature generality, which reduces the required number of training samples.Second, the intra-class variance can be largely reduced by grid partitioning. Third, SSFSP is a highly sparse feature, which reduces the dependence on the CNN model structure and enables early and fast convergence in model training. In conclusion, SSFSP has great potential for practical crop classification in precision agriculture.

Nonlinear modeling based on RBF neural networks identification and adaptive fuzzy control of DMFC stack

The temperature models of anode and cathode of direct methanol fuel cell （DMFC） stack were established by using radial basis function （RBF） neural networks identification technique to deal with the modeling and control problem of DMFC stack. An adaptive fuzzy neural networks temperature controller was designed based on the identification models established, and parameters of the controller were regulated by novel back propagation （BP） algorithm. Simulation results show that the RBF neural networks identification modeling method is correct, effective and the models established have good accuracy. Moreover, performance of the adaptive fuzzy neural networks temperature controller designed is superior.

Evaluation of Network Stack Optimization Techniques for Wireless Sensor Networks

We present a network stack implementation for a wireless sensor platform based on a byte-level radio. The network stack provides error-correction code, multi-channel capability and reliable communication for a high packet reception rate as well as a basic packet-level communication interface. In outdoor tests, the packet reception rate is close to 100% within 800 ft and is reasonably good up to 1100 ft. This is made possible by using error correction code and a reliable transport layer. Our implementation also allows us to choose a fre-quency among multiple channels. By using multiple frequencies as well as a reliable transport layer, we can achieve a high packet reception rate by paying additional retransmission time when collisions increase with additional sensor nodes.

Stacked Attention Networks for Referring Expressions Comprehension

Referring expressions comprehension is the task of locating the image region described by a natural language expression,which refer to the properties of the region or the relationships with other regions.Most previous work handles this problem by selecting the most relevant regions from a set of candidate regions,when there are many candidate regions in the set these methods are inefficient.Inspired by recent success of image captioning by using deep learning methods,in this paper we proposed a framework to understand the referring expressions by multiple steps of reasoning.We present a model for referring expressions comprehension by selecting the most relevant region directly from the image.The core of our model is a recurrent attention network which can be seen as an extension of Memory Network.The proposed model capable of improving the results by multiple computational hops.We evaluate the proposed model on two referring expression datasets:Visual Genome and Flickr30k Entities.The experimental results demonstrate that the proposed model outperform previous state-of-the-art methods both in accuracy and efficiency.We also conduct an ablation experiment to show that the performance of the model is not getting better with the increase of the attention layers.

Bi-LSTM-Based Deep Stacked Sequence-to-Sequence Autoencoder for Forecasting Solar Irradiation and Wind Speed

Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.

An Efficient Stacked Ensemble Model for Heart Disease Detection and Classification

Cardiac disease is a chronic condition that impairs the heart’s functionality.It includes conditions such as coronary artery disease,heart failure,arrhythmias,and valvular heart disease.These conditions can lead to serious complications and even be life-threatening if not detected and managed in time.Researchers have utilized Machine Learning(ML)and Deep Learning(DL)to identify heart abnormalities swiftly and consistently.Various approaches have been applied to predict and treat heart disease utilizing ML and DL.This paper proposes a Machine and Deep Learning-based Stacked Model(MDLSM)to predict heart disease accurately.ML approaches such as eXtreme Gradient Boosting(XGB),Random Forest(RF),Naive Bayes(NB),Decision Tree(DT),and KNearest Neighbor(KNN),along with two DL models:Deep Neural Network(DNN)and Fine Tuned Deep Neural Network(FT-DNN)are used to detect heart disease.These models rely on electronic medical data that increases the likelihood of correctly identifying and diagnosing heart disease.Well-known evaluation measures(i.e.,accuracy,precision,recall,F1-score,confusion matrix,and area under the Receiver Operating Characteristic(ROC)curve)are employed to check the efficacy of the proposed approach.Results reveal that the MDLSM achieves 94.14%prediction accuracy,which is 8.30%better than the results from the baseline experiments recommending our proposed approach for identifying and diagnosing heart disease.

融合改进自编码器和残差网络的入侵检测模型

互联网中存在大量隐私数据,因此防止网络入侵成为保护网络安全的关键问题。为提高网络入侵检测的准确率并解决其收敛慢问题,设计一种改进的堆叠自动编码器和残差网络(ISAE-ResNet)入侵检测模型。融合栈式自编码器和残差网络,首先将预处理后的数据输入到改进的栈式自编码器中,该栈式自编码器由2个副编码器和1个主编码器组成,数据经过副编码器和主编码器训练后重构出新的特征来防止过拟合问题;然后将解码层的权重捆绑到编码层进行优化,使模型参数减半来进行降维,提高模型的收敛速度;最后将处理过的数据输入到改进的残差网络中,并基于改进的ResNet网络设计一种加入软阈值函数的残差模块,通过降低数据中的噪声来提高模型准确率。在CIC-IDS-2017数据集上的实验结果表明,该模型准确率为98.67%,真正例率为95.93%,误报率为0.37%,损失函数值快速收敛至0.042,在准确率、真正例率、误报率和收敛速度方面均超过对比入侵检测模型,具有较高的有效性和可行性。

基于双层DCT-Mask特征融合算法的堆叠垃圾实例分割

复杂堆叠场景下的垃圾实例分割受到严重遮挡和高密集性特点的影响,具有更大的检测难度。针对该问题,提出了一种结合DCT-Mask和双层特征融合网络思想的实例分割方法,用于高度堆叠场景下的垃圾实例分割。在网络结构层面,首先在数据预处理环节对特征数据进行解耦,并通过双分支特征融合降低堆叠对遮挡物体特征的影响,从而解决复杂堆叠遮挡下的实例分割问题。针对该场景下的密集混淆问题,在候选框分类回归部分融入了级联分类器,并优化了分割网络分支的损失函数。实验采用堆叠垃圾分类实例分割数据集进行实验验证,实验结果表明,该方法的AP_(50)、平均准确率mAP等指标有较大提升,且具有较好的分割效果和一定的可解释性。

基于深度SSDAE网络的刀具磨损状态识别

针对刀具磨损状态识别过程中采集数据量大、干扰信号复杂且需人为选择特征参数的问题,为提高刀具磨损状态识别模型的鲁棒性与泛化性,提出了一种数据驱动下深度堆叠稀疏降噪自编码(stacking sparse denoising auto-encoder,简称SSDAE)网络的刀具磨损状态识别方法,实现隐藏在数据中深层次的数据特征自动挖掘。首先,将原始振动信号分解为一系列固有模态分量(intrinsic mode function,简称IMF),并采用皮尔逊相关系数法选取了最优固有模态来组合一个新的信号;其次,采用SSDAE网络自适应提取特征后对刀具磨损阶段进行了状态识别,识别精度达到98%;最后,对网络模型进行实验验证,并与最常用的刀具磨损状态识别方法进行了对比。实验结果表明,所提出的方法能够很好地处理非平稳振动信号,对不同刀具磨损阶段状态的识别效果良好,并具有较好的泛化性能和可靠性。

融合Transformer和卷积LSTM的轨迹分类网络

为了减少原始轨迹数据的噪声,充分提取轨迹的时空特征,提高基于轨迹数据的交通模式分类精度,提出一种融合堆叠降噪自编码器、Transformer和卷积长短期记忆网络的轨迹分类网络(networks fusing stacked denoising auto-encoder, Transformer and ConvLSTM,SDAETC)。通过堆叠降噪自编码器减少原始轨迹数据中的噪声;利用结合了Transformer的递归图自编码器,提取到更为丰富的时间特征,同时利用特征图自编码器提取空间特征;改进卷积长短期记忆网络,充分提取轨迹中的时空特征,并与提取到的时间特征和空间特征相融合,从而实现交通模式分类。实验结果表明,提出的SDAETC与基线模型相比,在GeoLife和SHL数据集上的准确率分别提升了1.8%和2%。此外,消融实验结果和模型训练时间分析表明,引入堆叠降噪自编码器、Transfomer和ConvLSTM虽然增加了时间消耗,但是对分类精度有积极贡献。