An enhanced network service pricing model considering network externalities

In this paper, we provide an evaluation model for marketable quality and profitability. We define the marketable quality as a qualitative aspect of profitability. Not always there is a clear tradeoff relation between marketable quality and profitability. Therefore, it is important to discover how to increase the profitability by enhancing marketable quality. We apply the real values of some leading manufacturing Japanese corporations to our proposed model to analyze its accuracy. From the analysis, we found that theoretical and real standard values of the marketable quality indicator were both 0.6. This shows that the proposed model has a good approximation. From the fair relation of network service providers and consumers, we present the network pricing guidelines for the maximum profitability, while enhancing the marketable quality. Also, we enhance our proposed network service pricing model considering network externalities.     

QS-STT: QuadSection clustering and spatial-temporal trajectory model for location prediction

Location prediction is a crucial need for location-aware services and applications. Given an object’s recent movement and a future time, the goal of location prediction is to predict the location of the object at the future time specified. Different from traditional location prediction using motion function, some research works have elaborated on mining movement behavior from historical trajectories for location prediction. Without loss of generality, given a set of trajectories of an object, prior works on mining movement behaviors will first extract regions of popularity, in which the object frequently appears, and then discover the sequential relationships among regions. However, the quality of the frequent regions extracted affects the accuracy of the location prediction. Furthermore, trajectory data has both spatial and temporal information. To further enhance the accuracy of location prediction, one could utilize not only spatial information but also temporal information to predict the locations of objects. In this paper, we propose a framework QS-STT (standing for QuadSection clustering and Spatial-Temporal Trajectory model) to capture the movement behaviors of objects for location prediction. Specifically, we have developed QuadSection clustering to extract a reasonable and near-optimal set of frequent regions. Then, based on the set of frequent regions, we propose a spatial-temporal trajectory model to explore the object’s movement behavior as a probabilistic suffix tree with both spatial and temporal information of movements. Note that STT is not only able to discover sequential relationships among regions but also derives the corresponding probabilities of time, indicating when the object appears in each region. Based on STT, we further propose an algorithm to traverse STT for location prediction. By enhancing the quality of the frequent region extracted and exploring both the spatial and temporal information of STT, the accuracy of location prediction in QS-STT is improved. QS-STT is designed for individual location prediction. For verifying the effectiveness of QS-STT for location prediction under the different spatial density, we have conducted experiments on four types of real trajectory datasets with different speed. The experimental results show that our proposed QS-STT is able to capture both spatial and temporal patterns of movement behaviors and by exploring QS-STT, our proposed prediction algorithm outperforms existing works.     

The sparse Luce model

The Luce model is one of the most popular ranking models used to estimate the ranks of items. In this study, we focus on grouping items with similar abilities and consider a new supervised clustering method by fusing specific parameters used in the Luce model. By modifying the penalty function conventionally used in grouping parameters, we obtain a new method of grouping items in the Luce model without pairwise comparison modeling and develop an efficient algorithm to estimate the parameters. Moreover, we give an application of the proposed algorithm to the Bradley-Terry model with ties. In the real data analysis, we confirm that the proposed estimator provides an easier interpretation of ranks and an improvement in the quality of prediction.     

Predicting molten steel endpoint temperature using a feature-weighted model optimized by mutual learning cuckoo search

A feature-weighted neural network model for the prediction of the endpoint temperature of molten steel (MSET) in a ladle furnace (LF) is proposed in this paper. Accurate prediction of MSET is essential for promoting product quality, reducing production costs and enhancing productivity. Considering that different features have different impacts on the MSET during the process of LF refining, a weight is applied to each feature before feeding the feature to neural networks. A mutual learning cuckoo search (MLCS) algorithm is proposed to simultaneously determine the feature weights and network parameters of the proposed prediction model. The search of each cuckoo in the basic cuckoo search algorithm and many of its variants is performed independently, which may decrease the algorithms’ performance. The proposed MLCS algorithm introduces two new search strategies, the mutual learning-based search strategy and the bottom reinforcement learning-based search strategy. The superior performance of MLCS is first confirmed with 20 benchmark optimization problems. Then, MLCS is applied to optimize the feature weights and network parameters in the feature-weighted MSET prediction model. Application to modeling the production data from a 300 t LF in an iron & steel plant in China demonstrates the effectiveness of the proposed feature-weighted neural network model.     

Two-stage online inference model for traffic pattern analysis and anomaly detection

In this paper, we propose a method for modeling trajectory patterns with both regional and velocity observations through the probabilistic topic model. By embedding Gaussian models into the discrete topic model framework, our method uses continuous velocity as well as regional observations unlike existing approaches. In addition, the proposed framework combined with Hidden Markov Model can cover the temporal transition of the scene state, which is useful in checking a violation of the rule that some conflict topics (e.g. two cross-traffic patterns) should not occur at the same time. To achieve online learning even with the complexity of the proposed model, we suggest a novel learning scheme instead of collapsed Gibbs sampling. The proposed two-stage greedy learning scheme is not only efficient at reducing the search space but also accurate in a way that the accuracy of online learning becomes not worse than that of the batch learning. To validate the performance of our method, experiments were conducted on various datasets. Experimental results show that our model explains satisfactorily the trajectory patterns with respect to scene understanding, anomaly detection, and prediction.     

基于BP神经网络的水质预测方法的研究

为了建立相应的水质预测和评价管理决策支持系统,在了解和分析一些常规水质模型的基础上,提出了用BP神经网络进行智能建模的方法,并结合东江自动监测站的实测水质数据进行了初步的探索,建立了东江水质预测的BP神经网络模型,并给出了仿真结果。结果表明,BP神经网络模型可以很好地对水质进行预测,解决系统中复杂的非线性关系,具有预测精度高,简便可靠等特点。     

基于时空相似LSTM的空气质量预测模型

由传统机器学习方法组成的空气质量预测模型得到了普遍应用,但是此类模型对于数据有效性,特别是时空相关数据的选取仍旧存在不足.针对深度学习输入数据有效性问题进行研究,提出了一种基于时空相似LSTM的预测模型(spatial-temporal similarity LSTM model,STS-LSTM),以便在时间和空间层面选取更加有效的数据.STS-LSTM分为前序、中序和后序三个模块,前序模块为时空相似选择输入模块,提出了格兰杰因果权重动态时间折叠(Granger causal index weighted dynamic time warping,GCWDTW)算法,用于选取具有更高时空相似性的数据;中序模块使用LSTM作为深度学习网络进行训练;后序模块根据目标站点特征选择不同的输出组合进行集成.STS-LSTM整体模型在空气质量预测误差上较现有算法提升了8％左右,经过有效性选取的数据对于模型精度达到了最高21％的提升.实验结果表明,对于有效数据的选取该算法取得了显著效果,将数据输入输出方法作为应用型深度学习网络的一部分,可以有效提升深度学习网络的最终效果.     

基于指标相关性的网络运维质量评估模型

传统网络运维评估方法存在两方面的问题：一是在指标选取、权重指定等关键步骤过于依赖领域专家经验,难以得到精确全面的评估结果;二是通信设备用户数量不断增加带来了海量的数据,数据又来自多个厂家以及多种设备,传统方法处理此类海量异构数据的效率较低。为了解决这些问题,提出基于指标间互相关性的指标选取方法。该方法着眼于评估过程中指标选取步骤,通过比较指标数据序列间的相关性强弱,对原始指标集进行分类,在各个簇中选择代表性指标完成关键指标体系的构建;另外,结合无人工参与的数据处理方法、权重确定方法建立了网络运维质量评估模型。在实验中,所提方法选取的指标对人工指标的覆盖率为72.2%,并且比人工指标的信息重叠率少31%。所提方法能够有效减少人力参与,且评估结果对告警有较好的预测准确率。     

长江水质预测的建模

分析了在长江水质的评价和预测建模过程中出现的一些问题,利用灰色模型的指数特性,建立预测长江水质的GM（1,1）的改进模型。根据数据的周期波动特性,采用灰色系统理论建立了残差序列周期修正GM（1,1）模型,用复合残差来修正预报数据,提高了数据预报的准确程度和模型的适用性。     

基于动态隶属度的模糊时间序列模型的水质预测研究

科学有效的水质预测对于水资源的管理与水污染预警尤为重要。由于水质指标序列存在非线性、非平稳性、模糊性和季节性等特点,传统预测模型的精度受到一定的限制。结合差分整合自回归移动平均ARIMA模型和经典模糊时间序列模型的特性,提出了一种基于动态隶属度的模糊时间序列水质预测新模型。首先,利用模糊C均值聚类从原始数据中构建隶属度序列;其次,利用经典的时间序列模型对不同的子隶属度序列进行预测,得到动态隶属度;最后,去模糊化得到水质指标的预测值。应用提出的新模型对岷江某断面的水质指标进行了短期预测,并与经典模糊时间序列模型和ARIMA乘积季节模型进行对比。实验结果表明,新模型在RMSE、MAPE和MAE上均优于经典模糊时间序列模型和ARIMA乘积季节模型,极大地提高了预测精度,可为水污染防治提供有价值的参考。     

Online monitoring and control of a cyber-physical manufacturing process under uncertainty

Recent technological advancements in computing, sensing and communication have led to the development of cyber-physical manufacturing processes, where a computing subsystem monitors the manufacturing process performance in real-time by analyzing sensor data and implements the necessary control to improve the product quality. This paper develops a predictive control framework where control actions are implemented after predicting the state of the manufacturing process or product quality at a future time using process models. In a cyber-physical manufacturing process, the product quality predictions may be affected by uncertainty sources from the computing subsystem (resource and communication uncertainty), manufacturing process (input uncertainty, process variability and modeling errors), and sensors (measurement uncertainty). In addition, due to the continuous interactions between the computing subsystem and the manufacturing process, these uncertainty sources may aggregate and compound over time. In some cases, some process parameters needed for model predictions may not be precisely known and may need to be derived from real time sensor data. This paper develops a dynamic Bayesian network approach, which enables the aggregation of multiple uncertainty sources, parameter estimation and robust prediction for online control. As the number of process parameters increase, their estimation using sensor data in real-time can be computationally expensive. To facilitate real-time analysis, variance-based global sensitivity analysis is used for dimension reduction. The proposed methodology of online monitoring and control under uncertainty, and dimension reduction, are illustrated for a cyber-physical turning process.

     

基于改进狼群算法的模糊时间序列预测模型

当使用模糊时间序列预测模型进行预测时, 模糊区间的不同划分对最后的预测精度有着十分重要的影响. 针对如何更有效的划分模糊区间、进一步提高模糊时间序列的预测精度问题, 本文提出了一种基于改进狼群算法 的模糊时间序列预测模型. 为此首先简要介绍了模糊时间序列, 然后阐述了狼群算法并在其游走行为中引入趋向 行为和死亡概率对其进行了改进, 最后利用改进狼群算法来划分模糊区间, 建立了一种新的模糊时间序列预测模 型. 将Alabama大学入学人数作为实验数据进行实例分析和验证. 通过与现有的一些模型进行对比分析, 本文所提 模型具有更高的预测精度, 为模糊时间序列预测提供了新思路.     

Formalizing and validating the web quality model for web source quality evaluation

The proposed web quality model (WebQM) is formalized with ISO/IEC Z language and empirically studied based on the Structural Equation Modeling (SEM) approach. By building the sample data set and constructing the structure equation model, the goodness-of-fit of WebQM is analyzed based on generalized least square method. A web source quality evaluation process based on validated WebQM is implemented and verified as more objective and credible, because the weights of quality criteria are automatically produced in the validation procedure, which avoids the subjective weight assignment in some classic assessment approaches. The model validation and implemented evaluation show that WebQM fits the real web source quality data and is feasible, reliable, and effective for web source quality evaluation.     

基于最优定权组合法的大气污染物SO2预测

为了提高对大气污染物SO₂的预测准确率,基于多个空气质量预测模式（WRF-CHEM、CMAQ、CAMx）,以过去一段时间内各单项空气质量预测模式的组合预测误差平方和最小为原则,构建出针对大气污染物SO₂的最优定权组合预测模型.选取2018年云南省楚雄、昭通、蒙自三个站点1至5月份的实际观测数据和前述三个空气质量模式的预测数据作为实验样本,然后分别采用多元线性回归法和动态权重更新法在相同的实验条件下与所提的最优定权组合预测法进行预测对比实验.实验结果表明,所提方法的预测值相较其他两种方法更加贴近实际观测值,其两项误差评估指标值均最小.总体而言,最优定权组合预测模型很好地综合了各单项空气质量预测模式的优势,提高了SO₂的预测精度.     

QSAR/QSPR模型中的蒙特卡罗交叉效验评价

介绍了用于QSAR或QSPR模型的蒙特卡罗(Monte Carlo)交叉效验模型评价方法。该方法是采用蒙特卡罗随机思想把数据集随机的分成训练集和预测集来对模型进行交叉效验,从模型的预测能力和预测稳定性两个方面评价模型。通过研究不同代表性的3套化学数据的结果表明,与k-折交叉效验相比,Monte Carlo交叉效验,是一种有效且稳定的QSAR或QSPR模型的评价方法。     

Utilizing transition information in online quality prediction of multiphase batch processes

In most previous researches, the data information of the transitions from one phase to another has been ignored, although it may be critical to product quality. In this paper, based on the cycle repeatability of batch processes, a repeatability factor is defined to divide the process into different steady phases and transition periods. Then an online quality prediction algorithm is proposed. In each steady phase where the process nature keeps similar, a representative phase model is developed; while in the transition period, a local modeling strategy is utilized for just-in-time modeling of each time slice, based on which only those batches having high similarities with the current batch are selected for modeling. Furthermore, a series of cumulative regression models are constructed for combining the results from different phases and transitions, which could further improve the prediction performance. Two examples are provided to demonstrate the feasibility and efficiency of the proposed method.     

煤气平衡认证分析系统的设计

针对流程工业中煤气的供耗平衡问题,本文以某钢铁企业为背景设计一个煤气平衡认证分析系统,系统由消耗预测、平衡认证、虚拟仪表、Web发布等模块组成,具有用户煤气消耗预测、煤气计量自动平衡、仪表远程校准、煤气数据Web发布等功能。系统的运行减少了煤气计量系统的误差,自动平衡认证了煤气的发生量与消耗量,对于企业的节能降耗具有重要意义。     

面向空气质量的时空混合预测模型

由于城市中各区域空气质量同时存在时间与空间维度上的相关性,而传统深度学习模型结构比较单一,并且难以从时空角度进行建模。针对该问题提出一种可以同时提取空气质量间复杂时空关系的STAQI模型用于空气质量预测。该模型由局部组件和全局组件构成,分别用于描述本地污染物浓度和邻近站点空气质量状况对目标站点空气质量预测产生的影响,并利用加权融合组件输出获得预测结果。在全局组件中,利用图卷积网络改进门控循环单元网络的输入部分,从而提取出输入数据中的空间特征。最后将STAQI模型与多种基准模型和变体模型进行对比。其中,STAQI模型与门控循环单元模型和全局组件变体模型相比,均方根误差（RMSE）分别下降约19%和16%。结果表明STAQI模型对于任意时间窗口都具有最佳预测性能,并且对不同目标站点的预测结果验证了该模型具有较强的泛化能力。     

改进的自回归AR（p）预测模型在WSN中的应用

自回归AR（p）预测模型是无线传感网络（WSN）中一种减少数据传输次数和降低能量消耗的方法。针对AR（p）模型在建模过程中忽略了不同时期的历史数据对预测值的影响存在的差异,导致模型预测精度不高、网络通信频率受影响的问题,提出了一种改进的预测模型FAR（p）。在AR（p）模型中引入一种新的模糊隶属度函数,通过模糊隶属度函数对预测模型的每个历史数据赋予权值,实现历史数据“重近轻远”的预测效果,并经二次加权平均算法处理后重新构建预测模型。仿真结果表明,改进的预测模型有效地提高了模型预测精度,减少了传感网络中数据传输次数,降低了能量消耗。     

基于分段线性表示和高斯过程分类的股票转折点概率预测

针对股票交易过程中价格转折点的预测问题,提出了一种基于分段线性表示(PLR)与高斯过程分类(GPC)相结合的股票价格转折点预测算法PLR-GPC。该算法通过PLR提取股票历史价格序列的转折点,对转折点进行分类标记,建立基于GPC的股票价格转折点预测模型,以上述股票历史价格序列对模型进行训练,最终由预测模型对股票价格转折点进行预测,并对预测结果进行概率解释。将PLR-GPC与基于BP神经网络(BPN)的PLR-BPN算法、基于加权支持向量机支持向量机(WSVM)的PLR-WSVM算法进行实验对比:PLR-GPC在预测准确率上高于PLR-BPN与PLR-WSVM;在投资收益率上高于PLR-BPN,与PLR-WSVM持平。实验结果表明PLR-GPC在股票价格转折点的预测上是有效的,并且可以应用在实际股票投资交易中。