基于LSTM的公共自行车服务点租还需求量预测

城市公共自行车系统（PBS）服务点自行车数量的再平衡是解决“租还车难”问题的关键,对服务点租还需求量的短时预测则是PBS再平衡的基础。通过分析PBS租还需求的内外关联影响因素,提出基于深度学习理论的LSTM（Long-Short Term Memory,长短时间记忆）单元的循环神经网络RNN（Recurrent Neural Network）服务点租还需求量预测模型,并通过区域PBS平均出行OD,对预测模型的输入特征进行合理优化,实现PBS服务点租还需求量的短时预测。以杭州市下沙PBS服务区为实验对象,选取三组不同的输入时间步长对预测模型进行实践验证,结果显示：在选取的模型结构与输入特征下,采用循环神经网络对服务点租还需求量进行预测能够比传统前馈神经网络在结果上更加接近实际值,并且精度较为满意,表明了该预测方法可行有效。     

基于SAE-ConvLSTM深度学习模型的多站城轨短时客流预测

为准确预测多个站点城轨交通短时客流,提出卷积长短时记忆网络（ConvLSTM）与栈式自编码器（SAE）相结合的深度学习模型SAE-ConvLSTM。考虑了13个影响客流量的外部因素,并通过SAE对其进行逐层提取,获得更具代表性的外部特征。通过ConvLSTM充分提取客流量的时间与空间特征,并融合所获得的外部特征对轨道交通网络中多个站点的短时客流量进行同步预测。同时设计了隐动作蒙特卡洛树搜索方法（LA-MCT）,对SAE进行参数寻优。为了验证寻优效果,与遗传算法、粒子群算法,模拟退火算法,以及禁忌搜索算法进行对比。结果表明,LA-MCTS在寻优时间和寻优效果方面均具有优势。此外,以深圳地铁为例进行大量的数值实验,结果显示在预测均方根误差、绝对误差均值、平均绝对百分比误差以及拟合优度方面,所构建的SAE-ConvLSTM模型预测结果均优于浅层机器学习模型—反向传播神经网络、支持向量回归模型、整合移动平均自回归模型,及深度学习模型—长短时记忆网络、卷积神经网络、以及不加入外部特征的ConvLSTM、加外部特征无SAE的ConvLSTM、长短时记忆网络+卷积神经网络（CNN+LSTM）和加外部特征的CNN+LSTM。     

基于CNN和GRU的混合股指预测模型研究

针对股票数据共线性和非线性的特点,提出了一种基于卷积神经网络（Convolutional Neural Network,CNN）和门控循环单元（Gated Recurrent Unit,GRU）神经网络的混合预测模型,并对沪深300指数、上证综指和深证成指进行了预测。该模型首先采用CNN提取特征向量,对原始数据进行降维,然后利用GRU神经网络学习特征动态变化规律进行股指预测。仿真结果表明,与GRU神经网络、长短时记忆（Long-Short-Term Memory,LSTM）神经网络和CNN相比,该模型能够挖掘历史数据中蕴含的信息,有效提高股指预测的准确率,并可为股指交易提供一些参考。     

长短时记忆网络在热力站建模中的应用

针对热力站为多变量、非线性、强耦合、大时滞的复杂时序控制系统,难以建立精确模型的问题,提出基于循环神经网络的长短时记忆算法对热力站控制系统建模,该算法既考虑到时间上的影响因素,又解决了长序列信息丢失的问题。以包头某热力站大量实时工况数据通过tensorflow框架搭建神经网络模型,仿真对比结果表明,长短时记忆网络建模能有效地减小建模误差,进一步提高神经网络在热力站系统建模中的精度。     

基于BiLSTM-CNN串行混合模型的文本情感分析

针对现有文本情感分析方法准确率不高、实时性不强以及特征提取不充分的问题,构建了双向长短时记忆神经网络和卷积神经网络（BiLSTM-CNN）的串行混合模型。首先,利用双向循环长短时记忆（BiLSTM）神经网络提取文本的上下文信息;然后,对已提取的上下文特征利用卷积神经网络（CNN）进行局部语义特征提取;最后,使用Softmax得出文本的情感倾向。通过与CNN、长短时记忆神经网络（LSTM）、BiLSTM等单一模型对比,所提出的文本情感分析模型在综合评价指标F1上分别提高了2.02个百分点、1.18个百分点和0.85个百分点;与长短时记忆神经网络和卷积神经网络（LSTM-CNN）、BiLSTM-CNN并行特征融合等混合模型对比,所提出的文本情感分析模型在综合评价指标F1上分别提高了1.86个百分点和0.76个百分点。实验结果表明,基于BiLSTM-CNN的串行混合模型在实际应用中具有较大的价值。     

基于深度聚合神经网络的网约车需求时空热度预测

为解决服务车辆与乘客间的供需不平衡问题,提升服务车辆的运营效率和利润,同时降低乘客等待时间并改善其对服务平台的满意度,针对差异化结构的多维时空数据,提出一种深度聚合神经网络（DANN）模型用于对网约车需求进行预测。首先,通过综合考虑时间、空间和外部环境等多维影响因素,提出了基于周期的时空变量和基于图像点值的空间变量划分方法;其次,依据数据特点构建了不同的子神经网络结构来分别拟合时间变量、空间变量和环境变量与需求间的非线性关系;然后,提出了多种异类子神经网络的聚合方法以同时捕捉不同结构时空数据的隐含特征;最后,分析了聚合权重的设置方法以获得网络模型的最优性能。实验结果表明,在三个真实数据集上所提模型的R²平均误差仅为9.36%,与卷积长短时记忆网络（FCL-Net）和混合深度学习神经网络（HDLN-Net）模型相比,所提模型的R²分别平均提升了4.6%和5.22%,均方误差（MSE）分别平均降低了27.01%和26.6%。因此,DANN在实际应用中能较大幅度地提升需求预测的准确性,可以作为网约车需求预测的有效手段。     

上下文感知的树递归神经网络下隐式情感分析

针对现有的序列化模型对中文隐式情感分析中特征信息提取不准确以及对篇章级的文本信息提取存在的梯度爆炸或者梯度消失的问题,提出了双向长短时神经网络和上下文感知的树形递归神经网络（context-aware tree recurrent neutral network,CA-TRNN）的并行混合模型。该模型分别利用双向循环长短时记忆神经网络（BiLSTM）提取文本中的上下文信息,树形递归神经网络（TRNN）提取文本中目标句的语义特征信息,最后,使用特定目标句的注意力机制将两个表示信息进行融合表示后,经过softmax得出文本的情感分类结果。采用SMP2019微博中文隐式情感分析任务中的数据进行验证,实验结果表明,所使用的模型（CA-TRNN）可以有效提高分类结果的准确度,时间代价小,具有更好的应用能力。     

使用深度长短时记忆模型对于评价词和评价对象的联合抽取

评价词和评价对象抽取在意见挖掘中是一个重要的任务,我们在句子级评价词和评价对象联合抽取任务上研究了长短时记忆(long short-term memory)神经网络模型的几种变种应用。长短时记忆神经网络模型是一种循环神经网络模型,该模型使用长短时记忆模型单元作为循环神经网络的记忆单元,它能够获得更多的长距离上下文信息,同时避免了普通循环神经网络的梯度消失和梯度爆炸的问题。我们对比了传统的方法,实验结果证明长短时记忆神经网络模型优于以前的方法,在细粒度评价词和评价对象的联合抽取中达到更好的性能。     

基于循环神经网络的电信行业容量数据预测方法

在电信运维的容量预测过程中,存在容量指标和部署业务种类繁多的问题。现有研究未考虑指标数据类型的差异,对所有类型的数据使用同种预测方法,使得预测效果参差不齐。为了提升指标预测效率,提出一种指标数据类型分类方法,利用该方法将数据类型分为趋势型、周期型和不规则型。针对其中的周期型数据预测,提出基于双向循环神经网络（BiRNN）的周期型容量指标预测模型,记作BiRNN-BiLSTM-BI。首先,为分析容量数据的周期特征,提出一种忙闲分布分析算法;其次,搭建循环神经网络（RNN）模型,该模型包含一层BiRNN和一层双向长短时记忆网络（BiLSTM）;最后,充分利用系统忙闲分布信息,对BiRNN输出的结果进行优化。与传统的三次指数平滑、差分自回归移动平均（ARIMA）模型和反向传播（BP）神经网络模型进行比较的实验结果表明,在统一日志数据集和分布式缓存数据集上,提出的BiRNN-BiLSTM-BI模型的均方误差（MSE）分别比对比模型中表现最优的模型降低了15.16%和45.67%,可见预测准确率得到了很大程度的提升。     

基于WOA-BiLSTM模型的空气质量指数预测

空气质量预测工作对于人们的生活日常出行具有非常重要的意义. 长短时记忆网络作为一种新型的深度学习循环神经网络, 对于时间序列数据表现出良好的预测能力. 但是针对神经网络模型在训练过程中一般凭借经验进行参数选择, 训练周期长, 预测精度低, 结果不可靠的问题, 本文提出了一种基于鲸鱼优化算法的双向长短时记忆网络模型, 即WOA (whale optimization algorithm)-BiLSTM (bidirectional long short-term memory)模型. 双向长短时记忆网络凭借其前向和后向的双向网络结构, 能够加强序列数据信息的记忆能力, 而WOA算法可以依据鲸鱼捕食时气泡网捕食的方法, 协助BiLSTM模型在训练过程中找到最优的网络参数. 将该模型用于陕西省AQI (air quality index)预测, 并分别和BiLSTM、LSTM模型进行对比, 发现本文提出的模型预测结果最好, MAE值为6.543 3, R²值达0.989 9. 将该模型用于空气质量预测领域具有良好的理论和实践意义.     

System Dynamics Forecasting on Taiwan Power Supply Chain

This research aims to study the sustainability of Taiwan power supply chain based on system dynamics forecasting. The paper tries to investigate electricity shortage effects not only on the industrial side, but also from the standpoint of society. In our model, different forecasting methods such as linear regression, time series analysis, and gray forecasting are also considered to predict the parameters. Further tests such as the structure, dimension, historical fit, and sensitivity of the model are also conducted in this paper. Through analysis forecasting result, we believe that the demand for electricity in Taiwan will continue to increase to a certain level for a period of time in the future. This phenomenon is closely related to Taiwan’s economic development, especially industrial development. We also point out that electricity prices in Taiwan do not match with high industrial demand, and that prices are still slightly low. Finally, the future growth trend of Taiwan’s electricity demand has not changed, and ensuring adequate supply to meet electricity demand to prevent potential power shortages will pose some difficulty.     

Daily Urban Water Demand Forecasting Based on Chaotic Theory and Continuous Deep Belief Neural Network

The prediction of daily water demands is a crucial part of the effective functioning of the water supply system. This work proposed that a continuous deep belief neural network (CDBNN) model based on the chaotic theory should be implemented to predict the daily water demand time series in Zhuzhou, China. CDBNN should initially be used to predict the urban water demand time series. First, the power spectrum and the largest Lyapunov exponent is used to determine the chaotic characteristic of the daily water demand time series. Second, C–C method is utilized to reconstruct the water demand time series’ phase space. Lastly, the forecasting model should be produced with the continuous deep belief network and neural network algorithms implemented for feature learning and regression, respectively, and the CDBNN input established by the best embedding dimension of the reconstructed phase space. The proposed method is contrasted with the support vector regression, generalized regression neural networks and feed forward neural networks, and they are accepted with the identical dataset. The predictive performance of the models is examined using normalized root-mean-square error (NRMSE), correlation coefficient (COR), and mean absolute percentage error (MAPE). The results suggest that the hybrid model has the smallest NRMSE and MAPE values, and the largest COR.     

基于改进的蝗虫优化算法的红细胞供应预测方法

当前国内“血荒”问题比较严峻,血站与用血单位之间存在着血液供不应求的现象。针对这个问题,提出了一种基于改进的蝗虫优化算法的LSTM预测方法,用于对未来的红细胞供应情况进行预测,为血站工作人员在制定采血计划以及制备计划时提供有效的指导。该预测模型通过使用长短期记忆网络(Long-Short Term Memory Network,LSTM)来捕捉历史红细胞库存数据之间的潜在规律,以达到对未来的供应情况进行预测的效果。首先,针对蝗虫优化算法容易陷入局部最优、收敛速度较慢的问题,通过加入基于折射原理的反向学习机制与混沌映射,加快蝗虫优化算法的收敛速度,使其具备更强的搜索能力。其次,为提高LSTM的预测性能,将改进的蝗虫优化算法与LSTM相结合,并使用某地区的红细胞库存真实数据作为实验数据,用于验证改进的LSTM预测模型的性能。与标准LSTM相比,所提方法的MAE,MAPE,RMSE分别降低了39.8278,1.10%,55.8191。实验结果证明,提出的方法具有较高的可靠性。     

多产品相互制约条件下的制造业产品需求预测研究

供应链环境中,产品需求预测对于制造业安排生产计划具有导向作用。对于大多数制造企业,通常生产的同一系列产品下有多种型号产品。由于受产能及市场容量限制,同系列下多型号产品之间对各自产品需求会产生相互影响作用。鉴于此,考虑历史需求数据在时间序列上的相邻关联性,研究在不同时间序列上各型号产品相互制约影响下产生的不同需求形态。同时考虑产品自身属性差异、供应链环境等影响因素,预测出某型号产品未来一段时间内的需求量。通过GRU-BP组合神经网络预测模型,对模型分析求解后证明预测结果的可行性。     

Fuzzy neural networks-based quality prediction system for sinteringprocess

A hybrid fuzzy neural networks and genetic algorithm (GA) system is proposed to solve the difficult and challenging problem of constructing a system model from the given input and output data to predict the quality of chemical components of the finished sintering mineral. A bidirectional fuzzy neural network (BFNN) is proposed to represent the fuzzy model and realize the fuzzy inference. The learning process of BFNN is divided into off-line and online learning. In off-line learning, the GA is used to train the BFNN and construct a system model based on the training data. During online operation, the algorithm inherited from the principle of backpropagation is used to adjust the network parameters and improve the system precision in each sampling period. The process of constructing a system model is introduced in details. The results obtained from the actual prediction demonstrate that the performance and capability of the proposed system are superior     

基于出行需求的城市车辆共享模式演化分析

车辆共享从资源分配的角度提高了汽车资源利用率.为了激励车辆共享,有关出行需求和出行者体验的研究势在必行.通过DBSCAN算法测量了城市内的交通需求聚集度,验证了车辆共享的可行性.确定了影响用户效用的关键因素,提出了基于Logit模型的数学模型以描述出行者体验和汽车资源利用率,预测出行者选择.同时,利用真实数据和调查结果,使测量和模型更加准确、真实.通过仿真实验,观测并分析了交通模式的演化过程及结果,发现城市出行需求量和交通需求聚集度是影响交通模式演化的主要因素.出行需求量需达到一定数值,演化才能达到稳定状态.城市出行交通需求聚集度越高,车辆共享的参与者则越多,其所获效用也越高.当出行需求量大于290,且交通需求聚集度大于0.9时,所有出行者都将选择车辆共享.最后,基于神州专车的出行数据,实验并观测了北京市交通模式的演化,发现若要在不加入经济因素或政策干预的情况下实施车辆共享,其交通模式将无法达到稳定状态.     

A hybrid extreme learning machine model with harris hawks optimisation algorithm: an optimised model for product demand forecasting applications

Accurate and real-time product demand forecasting is the need of the hour in the world of supply chain management. Predicting future product demand from historical sales data is a highly non-linear problem, subject to various external and environmental factors. In this work, we propose an optimised forecasting model - an extreme learning machine (ELM) model coupled with the Harris Hawks optimisation (HHO) algorithm to forecast product demand in an e-commerce company. ELM is preferred over traditional neural networks mainly due to its fast computational speed, which allows efficient demand forecasting in real-time. Our ELM-HHO model performed significantly better than ARIMA models that are commonly used in industries to forecast product demand. The performance of the proposed ELM-HHO model was also compared with traditional ELM, ELM auto-tuned using Bayesian Optimisation (ELM-BO), Gated Recurrent Unit (GRU) based recurrent neural network and Long Short Term Memory (LSTM) recurrent neural network models. Different performance metrics, i.e., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) were used for the comparison of the selected models. Horizon forecasting at 3 days and 7 days ahead was also performed using the proposed approach. The results revealed that the proposed approach is superior to traditional product demand forecasting models in terms of prediction accuracy and it can be applied in real-time to predict future product demand based on the previous week’s sales data. In particular, considering RMSE of forecasting, the proposed ELM-HHO model performed 62.73% better than the statistical ARIMA(7,1,0) model, 40.73% better than the neural network based GRU model, 34.05% better than the neural network based LSTM model, 27.16% better than the traditional non-optimised ELM model with 100 hidden nodes and 11.63% better than the ELM-BO model in forecasting product demand for future 3 months. The novelty of the proposed approach lies in the way the fast computational speed of ELMs has been combined with the accuracy gained by tuning hyperparameters using HHO. An increased number of hyperparameters has been optimised in our methodology compared to available models. The majority of approaches to improve the accuracy of ELM so far have only focused on tuning the weights and the biases of the hidden layer. In our hybrid model, we tune the number of hidden nodes, the number of input time lags and even the type of activation function used in the hidden layer in addition to tuning the weights and the biases. This has resulted in a significant increase in accuracy over previous methods. Our work presents an original way of performing product demand forecasting in real-time in industry with highly accurate results which are much better than pre-existing demand forecasting models.

     

A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price

Creating an intelligent system that can accurately predict stock price in a robust way has always been a subject of great interest for many investors and financial analysts. Predicting future trends of financial markets is more remarkable these days especially after the recent global financial crisis. So traders who access to a powerful engine for extracting helpful information throw raw data can meet the success. In this paper we propose a new intelligent model in a multi-agent framework called bat-neural network multi-agent system (BNNMAS) to predict stock price. The model performs in a four layer multi-agent framework to predict eight years of DAX stock price in quarterly periods. The capability of BNNMAS is evaluated by applying both on fundamental and technical DAX stock price data and comparing the outcomes with the results of other methods such as genetic algorithm neural network (GANN) and some standard models like generalized regression neural network (GRNN), etc. The model tested for predicting DAX stock price a period of time that global financial crisis was faced to economics. The results show that BNNMAS significantly performs accurate and reliable, so it can be considered as a suitable tool for predicting stock price specially in a long term periods.     

泊松分布灰色理论在物流需求预测中的应用

研究物流需求预测准确度问题。物流需求预测中存在数据小以及非线性特点,使预测系统存在不确定性。为解决上述问题,提出了一种泊松分布的神经网络需求预测算法,采用泊松分布算法对物流的整体需求进行分类,然后采用灰色理论算法选择物流需求影响因子,对物流的需求进行实时预测,仿真结果表明,改进物流需求预测方法比传统的灰色理论预测模型以及BP神经网络具有更高的预测精确度,有效地提高了区域物流需求的预测准确度,具有一定的实际应用价值。     

Forecasting warranty performance in the presence of the ‘maturing data’ phenomenon

Forecasting of warranty performance helps car engineers to fine-tune their strategies for warranty cost reduction. The forecasting process involves prediction of not only the specific months-in-service (MIS) warranty performance at a certain future time, but also future MIS values. However, the ‘maturing data’ phenomenon that causes a warranty performance measure at specific MIS values to change with time make such forecasting challenging. Although dynamic linear models have been used for forecasting warranty performance, the focus mainly has been to utilize previous-model-year vehicle data for the analysis. In this paper, we apply a neural network model to forecast year-end warranty performance in the presence of the ‘maturing data’ phenomenon. We use a special type of neural network, viz. radial basis function (RBF), and optimize its parameters by minimizing training and testing errors through planned experimentation. This application shows the effectiveness of RBF neural networks to forecast warranty performance in the presence of the ‘maturing data’ phenomenon.