基于t-SNE降维预处理的网络流量异常检测

网络流量中大多数流量都是正常的,但经常会出现偏离正常范围的异常流量,主要由DDOS攻击、渗透攻击等恶意的网络行为引起,这些异常行为通常会导致网络质量下降,甚至网络直接瘫痪。因此引入网络安全态势的预测,在仅知道正常网络流量的情况下判断网络中的异常。异常检测是一种网络安全态势的预测方法,用来判断网络中是否有异常。现有的异常检测算法由于无法准确提取网络数据包的低维特征导致算法的性能不佳,因此,需要找到网络数据包的准确的低维特征表示,该低维特征表示能够区分网络数据包是正常的还是有攻击的。为此,本文引入基于t-SNE降维的NLOF异常检测算法。该算法采用t-SNE算法自动预处理网络数据包以获得低维的网络数据包特征,之后将得到的低维的网络数据包特征作为NLOF算法的输入进行异常检测。其中,本文的NLOF算法首先采用k-means算法将网络数据包聚类成为K个簇,并将网络数据包数量小于N个的簇标记为异常簇,之后将未被标记为异常簇的网络数据包作为LOF算法的输入进行异常检测。在ISCX2012数据集上的实验结果表明,基于t-SNE降维的LOF算法达到最优性能时,准确率为98.46%,精确度为98.38%,检测率为98.54%,FAR为0.66%。该算法比基于现有最新算法的准确率、检测率和F1分别高3.18个百分点、0.02个百分点和0.01个百分点。基于t-SNE降维的NLOF算法达到最优性能时,准确率为98.53%,精确度为98.86%,检测率为98.86%,FAR为0.32%。该算法比基于现有最新算法的准确率、检测率和F1分别高3.25个百分点、0.34个百分点和0.41个百分点。这是异常检测中首次采用t-SNE算法自动提取低维的网络数据包特征。此外,LOF算法仅能捕获异常点,而本文的NLOF算法能够同时捕获异常点和异常簇。     

Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning

Prediction of wind speed can provide a reference for the reliable utilization of wind energy. This study focuses on 1-hour, 1-step ahead deterministic wind speed prediction with only wind speed as input. To consider the time-varying characteristics of wind speed series, a dynamic ensemble wind speed prediction model based on deep reinforcement learning is proposed. It includes ensemble learning, multi-objective optimization, and deep reinforcement learning to ensure effectiveness. In part A, deep echo state network enhanced by real-time wavelet packet decomposition is used to construct base models with different vanishing moments. The variety of vanishing moments naturally guarantees the diversity of base models. In part B, multi-objective optimization is adopted to determine the combination weights of base models. The bias and variance of ensemble model are synchronously minimized to improve generalization ability. In part C, the non-dominated solutions of combination weights are embedded into a deep reinforcement learning environment to achieve dynamic selection. By reasonably designing the reinforcement learning environment, it can dynamically select non-dominated solution in each prediction according to the time-varying characteristics of wind speed. Four actual wind speed series are used to validate the proposed dynamic ensemble model. The results show that: (a) The proposed dynamic ensemble model is competitive for wind speed prediction. It significantly outperforms five classic intelligent prediction models and six ensemble methods; (b) Every part of the proposed model is indispensable to improve the prediction accuracy.     

A novel deep learning prediction model for concrete dam displacements using interpretable mixed attention mechanism

Dam displacements can effectively reflect its operational status, and thus establishing a reliable displacement prediction model is important for dam health monitoring. The majority of the existing data-driven models, however, focus on static regression relationships, which cannot capture the long-term temporal dependencies and adaptively select the most relevant influencing factors to perform predictions. Moreover, the emerging modeling tools such as machine learning (ML) and deep learning (DL) are mostly black-box models, which makes their physical interpretation challenging and greatly limits their practical engineering applications. To address these issues, this paper proposes an interpretable mixed attention mechanism long short-term memory (MAM-LSTM) model based on an encoder-decoder architecture, which is formulated in two stages. In the encoder stage, a factor attention mechanism is developed to adaptively select the highly influential factors at each time step by referring to the previous hidden state. In the decoder stage, a temporal attention mechanism is introduced to properly extract the key time segments by identifying the relevant hidden states across all the time steps. For interpretation purpose, our emphasis is placed on the quantification and visualization of factor and temporal attention weights. Finally, the effectiveness of the proposed model is verified using monitoring data collected from a real-world dam, where its accuracy is compared to a classical statistical model, conventional ML models, and homogeneous DL models. The comparison demonstrates that the MAM-LSTM model outperforms the other models in most cases. Furthermore, the interpretation of global attention weights confirms the physical rationality of our attention-based model. This work addresses the research gap in interpretable artificial intelligence for dam displacement prediction and delivers a model with both high-accuracy and interpretability.     

基于数据挖掘的航空装备故障成品预测模型

因航空装备系统复杂度高,故障成因复杂,在保障时根据故障现象判断故障成品的难度很大,同时大量的历史故障记录数据未能有效利用.通过分析航空装备成品故障记录的特点,提出了一种基于数据挖掘的航空装备故障成品预测模型.该模型将历史故障记录数据作为输入,通过文本聚类将大量故障描述聚类得到故障现象簇,并建立"故障现象"与"故障成品"之间的多对多关系,提出了故障成品概率分布算法,并通过匹配新发生故障现象与故障现象簇,计算出故障成品概率分布.实验验证结果表明,该模型可有效地根据故障描述预测可能发生故障的成品的概率分布,且预测准确率可随数据量的增加而提高,满足实际保障需求.     

基于国产处理器增量式实时交通流预测算法及实现

针对城市交通难以处理大量数据且实时性差等问题,提出了根据增量式城市交通流数据预测拥堵情况的一种基于国产处理器的L-BFGS(limited-memory BFGS)算法。该算法通过存储向量序列计算Hessian矩阵,改进Two-Loop算法求下降方向,在Spark集群中并行处理时收敛速度快,适用于实时性要求强的城市交通场景。实验结果证明,L-BFGS预测算法完全可以在国产平台上对大规模的实时交通数据流进行快速建模、预测,在改善城市交通管理水平提供有效支撑的同时也丰富了国产芯片的应用领域。     

基于共同邻居邻域拓扑稠密性加权的链路预测方法

链路预测旨在利用已知的网络节点和拓扑结构信息,预测网络中未连接的两个节点之间存在连边的可能性。基于网络拓扑相似性的链路预测方法计算复杂度低且预测效果好,但现有的相似性指标对共同邻居的邻域拓扑信息考虑较少。针对此问题,提出一种基于共同邻居邻域拓扑稠密性加权的链路预测方法。首先,基于邻域拓扑相对稠密指数量化节点的邻域拓扑结构;然后,利用共同邻居的节点度和邻域拓扑相对稠密指数刻画共同邻居及其邻域拓扑的相似性贡献;最后,提出基于共同邻居邻域拓扑稠密性加权的节点相似性指标。在多个实际网络数据上的实验结果表明,与现有相似性指标相比,该方法能够取得更高的预测精度。     

基于多种信息组合模式的非负矩阵分解链路预测模型

针对基于拓扑结构相似性的链路预测算法中网络稀疏性和噪声问题,提出一种基于非负矩阵分解的链路预测模型。该模型从微观与宏观两个层面出发,融合网络内部和外部的辅助信息,减轻了网络稀疏性造成的影响,提升了算法预测的整体性能。提出的三种信息组合模式体现出宏观与微观角度下的信息融合策略。在13个真实网络数据集上的实验结果展示了算法预测性能上的优越性。     

无线可充能传感器网络的锚点算法与移动设备调度研究

由于传感器的电池容量和存储容量有限,导致无法持续对传感器进行能量补充并收集传感器生成的感测数据。针对该问题,研究了周期性能量补充和数据收集问题,提出了一种用于充能和数据收集的方法,包括基于网格的算法(GBA)、基于支配集的算法(DSBA)和基于圆相交的算法(CIBA)。通过这三种方法或两两相结合的方法找到锚点集合,通过移动设备调度算法调度最小数量的移动设备来访问生成的锚点。仿真结果验证了所提方法的有效性。与联合能量数据采集(JEDA)算法、最小覆盖圆(SEC)算法相比,所提CIBA需要的移动设备数量最少,总移动距离也最短,具有良好的综合性能。     

基于改进粒子群优化和极限学习机的网络安全态势预测

针对网络安全态势预测模型预测精度不高、收敛较慢等问题,提出了一种基于改进粒子群优化极限学习机（IPSO-ELM）算法的预测方法。首先,通过改进粒子群优化（PSO）算法中的惯性权重和学习因子来实现两种参数随着迭代次数增加的自适应调整,使PSO初期搜索范围大、速度高,后期收敛能力强、稳定。其次,针对PSO易陷入局部最优的问题,提出一种粒子停滞扰动策略,将陷入局部最优的粒子重新引导至全局最优飞行。改进粒子群优化（IPSO）算法既保证了全局寻优的能力,又对局部搜索能力有所增强。最后,将IPSO与极限学习机（ELM）结合来优化ELM的初始权值及阈值。与ELM相比,结合IPSO的ELM的预测精度提高了44.25%。实验结果表明,与PSO-ELM相比,IPSO-ELM的预测结果拟合度可达到0.99,收敛速度提升了47.43%。所提算法在预测精度和收敛速度等指标上明显优于对比算法。