基于A-DLSTM夹层网络结构的电能消耗预测方法

全球人口的快速增长和技术进步极大地提高了世界的总发电量,电能消耗预测对于电力系统调度和发电量管理发挥着重要的作用,为了提高电能消耗的预测精度,针对能耗数据的复杂时序特性,文中提出了一种将注意力机制(Attention)放置于双层长短期记忆人工神经网络(Double layer Long Short-Term Memory,DLSTM)中的新颖夹层结构,即A-DLSTM。该网络结构利用夹层中的注意力机制自适应地关注单个时间单元中不同的特征量,通过双层LSTM网络对序列中的时间信息进行抓取,以对序列数据进行预测。文中的实验数据为UCI机器学习数据集上某家庭近5年的用电量,采用网格搜索法进行调参,实验对比了A-DLSTM与现有的模型在能耗数据上的预测性能,文中的网络结构在均方误差、均方根误差、平均绝对误差、平均绝对百分比误差上均达到了最优,且通过热力图对注意力层进行了分析,确定了对用电量预测影响最大的因素。     

Gene expression time series modeling with principal component and neural network

In this work, gene expression time series models have been constructed by using principal component analysis (PCA) and neural network (NN). The main contribution of this paper is to develop a methodology for modeling numerical gene expression time series. The PCA-NN prediction models are compared with other popular continuous prediction methods. The proposed model can give us the extracted features from the gene expressions time series and the orders of the prediction accuracies. Therefore, the model can help practitioners to gain a better understanding of a cell cycle, and to find the dependency of genes, which is useful for drug discoveries. Based on the results of two public real datasets, the PCA-NN method outperforms the other continuous prediction methods. In the time series model, we adapt Akaike's information criteria (AIC) tests and cross-validation to select a suitable NN model to avoid the overparameterized problem.     

Mining partial periodic correlations in time series

Recently, periodic pattern mining from time series data has been studied extensively. However, an interesting type of periodic pattern, called partial periodic (PP) correlation in this paper, has not been investigated. An example of PP correlation is that power consumption is high either on Monday or Tuesday but not on both days. In general, a PP correlation is a set of offsets within a particular period such that the data at these offsets are correlated with a certain user-desired strength. In the above example, the period is a week (7 days), and each day of the week is an offset of the period. PP correlations can provide insightful knowledge about the time series and can be used for predicting future values. This paper introduces an algorithm to mine time series for PP correlations based on the principal component analysis (PCA) method. Specifically, given a period, the algorithm maps the time series data to data points in a multidimensional space, where the dimensions correspond to the offsets within the period. A PP correlation is then equivalent to correlation of data when projected to a subset of the dimensions. The algorithm discovers, with one sequential scan of data, all those PP correlations (called minimum PP correlations) that are not unions of some other PP correlations. Experiments using both real and synthetic data sets show that the PCA-based algorithm is highly efficient and effective in finding the minimum PP correlations. Zhen He is a lecturer in the Department of Computer Science at La Trobe University. His main research areas are database systems optimization, time series mining, wireless sensor networks, and XML information retrieval. Prior to joining La Trobe University, he worked as a postdoctoral research associate in the University of Vermont. He holds Bachelors, Honors and Ph.D degrees in Computer Science from the Australian National University. X. Sean Wang received his Ph.D degree in Computer Science from the University of Southern California in 1992. He is currently the Dorothean Chair Professor in Computer Science at the University of Vermont. He has published widely in the general area of databases and information security, and was a recipient of the US National Science Foundation Research Initiation and CAREER awards. His research interests include database systems, information security, data mining, and sensor data processing. Byung Suk Lee is associate professor of Computer Science at the University of Vermont. His main research areas are database systems, data modeling, and information retrieval. He held positions in industry and academia: Gold Star Electric, Bell Communications Research, Datacom Global Communications, University of St. Thomas, and currently University of Vermont. He was also a visiting professor at Dartmouth College and a participating guest at Lawrence Livermore National Laboratory. He served on international conferences as a program committee member, a publicity chair, and a special session organizer, and also on US federal funding proposal review panel. He holds a BS degree from Seoul National University, MS from Korea Advanced Institute of Science and Technology, and Ph.D from Stanford University. Alan C. H. Ling is an assistant professor at Department of Computer Science in University of Vermont. His research interests include combinatorial design theory, coding theory, sequence designs, and applications of design theory.     

Study on the communication method for chaotic encryption in remote monitoring systems

In chaotic cryptosystems, it is recognized that using (very) high dimensional chaotic attractors for encrypting a given message may improve the privacy of chaotic encoding. In this paper, we study a kind of hyperchaotic systems by using some classical methods. The results show that besides the high dimension, the sub-Nyquist sampling interval (SI) is also an important factor that can improve the security of the chaotic cryptosystems. We use the method of time series analysis to verify the results.     

Asynchronism-based principal component analysis for time series data mining

Principal component analysis (PCA) is often applied to dimensionality reduction for time series data mining. However, the principle of PCA is based on the synchronous covariance, which is not very effective in some cases. In this paper, an asynchronism-based principal component analysis (APCA) is proposed to reduce the dimensionality of univariate time series. In the process of APCA, an asynchronous method based on dynamic time warping (DTW) is developed to obtain the interpolated time series which derive from the original ones. The correlation coefficient or covariance between the interpolated time series represents the correlation between the original ones. In this way, a novel and valid principal component analysis based on the asynchronous covariance is achieved to reduce the dimensionality. The results of several experiments demonstrate that the proposed approach APCA outperforms PCA for dimensionality reduction in the field of time series data mining.     

Dynamic process fault monitoring based on neural network and PCA

A newly developed method, NNPCA, integrates two data driven techniques, neural network (NN) and principal component analysis (PCA), for process monitoring. NN is used to summarize the operating process information into a nonlinear dynamic mathematical model. Chemical dynamic processes are so complex that they are presently ahead of theoretical methods from a fundamental physical standpoint. NN functions as the nonlinear dynamic operator to remove processes' nonlinear and dynamic characteristics. PCA is employed to generate simple monitoring charts based on the multivariable residuals derived from the difference between the process measurements and the neural network prediction. It can evaluate the current performance of the process. Examples from the recent monitoring practice in the industry and the large-scale system in the Tennessee Eastman process problem are presented to help the reader delve into the matter.     

基于CNN-LSTM的短期风电功率预测

短期风电功率预测对电力系统的安全稳定运行和能源的优化配置具有重要意义。鉴于卷积神经网络(CNN)高效的数据特征提取能力,以及长短期记忆网络(LSTM)描述时间序列长期依赖关系的能力。为了提高短期风电功率预测的精度,设计了一种基于CNN和LSTM的风电功率预测模型。该模型利用卷积神经网络对风电功率、风速、风向数据进行多层卷积和池化堆叠计算,提取风电功率相关数据的特征图谱。为了描述风电功率序列的时序依从关系,将图谱特征信息作为长短期记忆网络的输入信息,计算得到风电功率的预测结果。采用西班牙某风电场的实测数据进行模型预测精度验证。结果表明,该模型较LSTM、Elman模型具有更好的预测性能。     

融合统计方法和双向卷积LSTM的多维时序数据异常检测

通过数据分析进行异常检测,有助于准确识别异常行为,从而提高服务质量和决策能力。然而,由于多维时序数据的时空依赖性以及异常事件发生的随机性,现有方法仍然存在一定的局限性。针对上述问题,提出一种融合新型统计方法和双向卷积LSTM的多维时序数据异常检测方法MBCLE。该方法引入堆叠的中值滤波处理输入数据中的点异常并平滑数据波动;设计双向卷积长短期记忆网络（Bi-ConvLSTM）和双向长短期记忆网络（Bi-LSTM）相结合的预测器进行数据建模和预测;通过双向循环指数加权移动平均（BrEWMA）平滑预测误差;使用动态阈值方法计算阈值以检测上下文异常。实验结果表明,MBCLE具有良好的检测性能,各步骤均对性能提升有所贡献。     

Multivariate modelling of long memory processes with common components

A new approach to the modelling of common components in long memory processes is introduced. The approach is based on a two-step procedure relying on Fourier transform methods (first step) and principal components analysis (second step). Differently from other available methods, it allows the modelling of large data sets, both in terms of temporal and cross-sectional dimensions. Monte Carlo evidence, supporting the two-step estimation procedure, is also provided, as well as an empirical application to real data.     

Image-based quality monitoring system of limestone ore grades

In this study, an image analysis-based ore quality monitoring system was developed. The study was conducted at a limestone mine located in India. The samples were collected based on a stratified random sampling method, and images of these samples were taken in a simulated environment in a laboratory. The image preprocessing and segmentation were performed using different segmentation methods to extract morphological, colour and textural features. A total of 189 features was extracted during this study. Principal components analysis was conducted to reduce the feature vector for modeling purposes. Five principal components, which were extracted from the feature vectors, captured 95% of the total feature variance. A neural network model was used as a mapping function for ore grade prediction. The five principal components were used as input, and four grade attributes of limestone (CaO, Al₂O₃, Fe₂O₃ and SiO₂) were used as output. The developed model was then used for day to day quality monitoring at 3 different face locations of the mine. Results revealed that this technique can be successfully used for ore grade monitoring at the mine level in a controlled environment.     

基于时序数据的工作面设备故障预测研究

煤矿工作面设备通常由多个复杂系统模块组成,各模块间具有强耦合性,且设备故障机理复杂,在进行设备故障预测时需对设备的运行状态、环境数据、操作数据等进行实时监测,从而获取电气、机械、热工类多参数时序数据。提出一种基于时序数据对工作面设备进行故障预测的方法：首先,采用时序对齐算法将采集的设备监测数据对齐,即对监测数据的时间列重新排序,以时间列为关键值,各监测数据作为标签值填入,空缺值以前值填充;然后,根据故障表征现象和发生机理选取故障相关因素,通过Pearson相关系数分析法计算相关因素间的相关性,由此确定故障预测因素集;最后,采用长短期记忆（LSTM）网络建立工作面设备故障预测模型,以归一化的故障预测因素集作为LSTM预测模型的输入、故障作为输出,将迟滞时间段引入LSTM预测模型,实现了迟滞性故障的超前预测。以采煤机过热跳闸故障为例进行试验,通过分析得出故障预测因素集为{滚筒温度,滚筒电流,滚筒启停,牵引温度,变压器温度,摇臂温度},当LSTM网络细胞层数为10、隐藏细胞数为10、学习率为0.001、迭代次数为1 500、1次读取样本个数为120时,采煤机过热跳闸故障的迟滞时间为30 min,采用测试集进行故障预测时可实现超前26 min预测,与迟滞时间相差4 min,表明采用LSTM网络可基于时序数据有效实现工作面设备故障的超前预测。     

基于循环神经网络的通信卫星故障检测

随着现代航天事业的飞速发展,通信卫星的结构日益复杂,其故障也逐渐增多,通信卫星的故障检测已成为当前航天领域关注的重点问题。目前,各大航天机构对故障的检测仍以简单的上下限阈值检测为主,只能检测出少部分特定的故障。早期利用传统机器学习算法进行检测的研究也仅能检测出数量特征上的故障。针对传统的机器学习算法难以有效学习遥测数据趋势变化的问题,文中提出了基于长短时记忆(Long Short-term Memory,LSTM)网络的阈值化方法。通过LSTM预测模型来学习卫星遥测数据的趋势变化,同时以最大化相关系数与F1分数的方式为多维遥测数据的故障判定确定合适的阈值,此方式能够有效地通过卫星遥测数据的趋势变化来判断故障。实验数据采用某航天机构提供的时长为2年的24维通信卫星遥测数据,其核心模型LSTM网络在NVIDIA Corporation GP102[TITAN Xp]上训练,最终整体模型的准确率为99.34%,查准率为81.93%,查全率为94.62%。同时,与传统机器学习算法以及基于LSTM的非阈值方法进行对比,该模型的精度明显更高。实验结果表明,LSTM网络能够高效地学习到卫星遥测数据的...     

基于TG–LSTM神经网络的非完整时间序列预测

针对传统模型对含数据缺失的非完整时间序列预测精度不高的问题,利用长短期记忆(LSTM)神经网络强大的时序建模能力,提出一种带时间门的长短期记忆(TG–LSTM)神经网络.首先,提出一种能同时对输入值在线估计和输出值实时预测的TG–LSTM单元结构;其次,基于TG–LSTM结构设计一种网络的前向传播算法,实现输入填补和输出预测同步进行;然后,建立TG–LSTM神经网络的学习算法来对输入填补和输出预测任务整体训练;最后,通过在Mackey-glass基准数据集,月平均气温数据集和污水处理出水氨氮预测中的实验结果表明:与传统方法相比,TG–LSTM神经网络模型能以更高精度对非完整时间序列进行填补和预测.     

时滞多变量系统PCA优化建模

主元分析（PCA）在工业生产过程的产品质量控制与故障诊断等方面已得到广泛应用,然而当过程的变量间存在着未知时滞性时,必须确定数据间的对应关系,否则PCA模型将会不准．基于此,提出了PCA优化建模方法．该方法以过程变量间的时滞常数为优化变量,在分析PCA模型特点基础上,确定主成分个数和SPE统计量为综合目标函数,并建立模型约束条件,采用遗传算法求解．最后给出了仿真实例,证明了所提出方法的有效性．     

基于BiLSTM-CRF的关键词自动抽取

关键词自动抽取是自然语言处理(Natural Language Processing,NLP)的一项重要任务,给个性化推荐、网购等应用提供了重要的技术支撑。针对关键词自动抽取问题,提出一种新的基于双向长短期记忆网络条件随机场(Bidirectional Long Short-Term Memory Network Conditional Random Field,BiLSTM-CRF)的方法,并将该问题刻画为序列标注问题。首先,该方法通过对输入的文本进行建模,把文本表示为低维高密度的向量;然后,使用分类算法对各个词进行分类;最后,使用CRF对整个标注序列进行解码,得到最终结果。在一个大规模的真实数据中进行实验,结果表明该方法较基准系统性能提高约1个百分点。     

基于BERT和BiLSTM的语义槽填充

语义槽填充是对话系统中一项非常重要的任务,旨在为输入句子的每个单词标注正确的标签,其性能的好坏极大地影响着后续的对话管理模块.目前,使用深度学习方法解决该任务时,一般利用随机词向量或者预训练词向量作为模型的初始化词向量.但是,随机词向量存在不具备语义和语法信息的缺点;预训练词向量存在"一词一义"的缺点,无法为模型提供具...