采用改进型IHS变换的遥感图像融合算法

在分析亮度一色度-饱和度(IHS)变换影像融合方法的基础上,针对IHS变换存在光谱特征扭曲的局限性,提出了一种采用分辨率退化模型的基于IHS变换的局部回归分析融合方法.采用SPOT的全色影像和TM的多光谱影像为实验数据,经多个统计参数的定量分析以及Matlab仿真实验的验证表明,该方法在空间分辨率和光谱分辨率上都达到了较好的效果.     

多元线性回归分析在机组发电耗水率中的应用

多元线性回归分析是一个有广泛适用性的多元统计分析方法。本文利用葛洲坝发电站的部分数据,对葛洲坝发电站一段时间内的库水位、出库流量及其对应的机组耗水率利用多元线性回归进行建模分析。显然,对这个问题的深入研究,可以有效地认识各种因素对机组发电耗水率的影响程度,从而可以更好地对机组发电耗水率进行预测。     

The hierarchical Tobit model: A case study in Bayesian computing

In this paper we discuss the potentials of a new Bayesian inference tool, called the Gibbs sampler, for the analysis of the censored regression or Tobit model. Tobit models have a wide range of applications in empirical sciences, like econometrics and biometrics. The estimation results of the simple Tobit model will be compared to a hierarchical Tobit model, and the Gibbs sampling approach to the related classical algorithm of expectation-maximisation (EM). The underlying botanical example of this paper is concerned with the censoring mechanism in plant reproduction and proposes the Bayesian Tobit model for the growth relationship between the reproductive part and the rest of the plant.     

基于历史数据和多目标优化的测试用例排序方法

针对如何提高测试用例序列的揭错效率和回归测试效益问题,提出一种基于历史数据和多目标优化的测试用例排序方法。首先,根据测试用例的文本主题相似性和代码覆盖相似性对测试用例集进行聚类,并根据历史执行信息对测试用例间的执行失败关系进行关联规则挖掘,从而为后续过程做准备;然后,利用多目标优化算法对每个类簇内的测试用例进行排序,在此之后生成最终排序序列,使相似的测试用例分隔开;最后,利用测试用例间的关联规则,动态调整测试用例执行次序,从而使可能失败的测试用例优先执行,以进一步提高缺陷检测效率。与随机排序方法、基于聚类的排序方法、基于主题模型的排序方法、基于关联规则和多目标优化的排序方法相比,所提方法的平均故障检测率（APFD）平均值分别提高了12.59%、5.98%、3.01%和2.95%,基于成本的平均故障检测率（APFDc）平均值分别提高了17.17%、5.04%、5.08%和8.21%。实验结果表明,所提方法能有效提高回归测试效益。     

融合CNN-BiLSTM-Attention的集成学习价格预测

价格预测对于大宗农产品市场的稳定具有重要意义,但是大宗农产品价格与多种因素有着复杂的相关关系.针对当前价格预测中对数据完整性依赖性强与单一模型难以全面利用多种数据特征等问题,提出了一种将基于注意力机制的卷积双向长短期记忆神经网络(CNN-BiLSTM-Attention)、支持向量机回归(SVR)与LightGBM组合的增强式集成学习方法,并分别在包含历史交易、天气、汇率、油价等多种特征数据的数据集上进行了实验.实验以小麦和棉花价格预测为目标任务,使用互信息法进行特征选择,选择误差较低的CNN-BiLSTM-Attention模型作为基模型,与机器学习模型通过线性回归进行增强式集成学习.实验结果表明该集成学习方法在小麦及棉花数据集上预测结果的均方根误差(RMSE)值分别为12.812, 74.365,较之3个基模型分别降低11.00%, 0.94%、4.44%,1.99%与13.03%, 4.39%,能够有效降低价格预测的误差.     

Digital at the edge – antecedents and performance effects of boundary resource deployment

With business ecosystems digitalizing by the force of digital innovation, the deployment of boundary resources (such as application programming interfaces: APIs) becomes a strategic option across contexts. We distinguish between boundary resources that provide access openness and those that provide resource openness, and theorize the antecedents and consequences of their deployment. Employing panel data regressions to a longitudinal cross-industry dataset, we find that the digital knowledge base of the focal firm and the existence of potential digital complementors drive boundary resource deployment. Such deployment benefits firm performance depending on the firm’s market power. From our empirical analysis, we reveal a differentiated perspective on the quality of the confined openness provided by boundary resources as well as the embeddedness of their deployment in the rationales and motivations of the associated actors in digital business ecosystems. We complement the existent theoretical framework on boundary resources and provide valuable insights to managers reflecting about deploying boundary resources in a beneficial way.     

3D printing system: an innovation for small-scale manufacturing in home settings? – early adopters of 3D printing systems in China

This study investigates Chinese consumers’ adoption of the innovative 3D printing systems for small-scale manufacturing in home settings. Empirical studies were conducted in a survey with 256 participants. The number of significant determinants that affect an individual’s decision to adopt 3D printing systems has been identified by applying a model that integrates the Technology Acceptance Model and Innovation Diffusion Theory. A number of moderation effects of demographic variables (e.g. gender, design background) on the association between motivational variables and participants’ adoption have also been analysed with factor analysis, structural equation modelling and hierarchical regression. Our results shed some light on the characteristics of early adopters of home 3D printing systems in China. This study contributes to the early understanding of Chinese consumers’ adoption of innovative 3D printing systems.     

Cutting force and hole quality analysis in micro-drilling of CFRP

Micro-drilling in carbon fiber reinforced plastic (CFRP) composite material is challenging because this material machining is difficult due to anisotropic, abrasive and non-homogeneous properties and also downscaling of cutting process parameters affect the cutting forces and micro-drilled hole quality extensively. In this work, experimental results based statistical analysis is applied to investigate feed and cutting speed effect on cutting force components and hole quality. Analysis of variance based regression equation is used to predict cutting forces and hole quality and their trend are described by response surface methodology. Results show that roundness error and delamination factor have similar trends to those of radial forces and thrust force, respectively. Non-linear trends of cutting forces and hole quality errors are observed during downscaling of the micro-drill feed value. Optimization results show that cutting forces and hole quality errors are minimum at a feed value which is almost equal to the tool edge radius rather than at the lowest feed value. Therefore, the presented results clearly show the influences of size effects on cutting forces and hole quality parameters in micro-drilling of CFRP composite material.     

Revisiting Statistical Design and Analysis in Scientific Research

Statistics is essential to design experiments and interpret experimental results. Inappropriate use of the statistical analysis, however, often leads to a wrong conclusion. This concept article revisits basic concepts of statistics and provides a brief guideline of applying the statistical analysis for scientific research from designing experiments to analyzing and presenting the data.     

Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features. Electric kickboards are gradually growing in popularity in tourist and education-centric localities. In the upcoming arrival of electric kickboard vehicles, deploying a customer rental service is essential. Due to its free-floating nature, the shared electric kickboard is a common and practical means of transportation. Relocation plans for shared electric kickboards are required to increase the quality of service, and forecasting demand for their use in a specific region is crucial. Predicting demand accurately with small data is troublesome. Extensive data is necessary for training machine learning algorithms for effective prediction. Data generation is a method for expanding the amount of data that will be further accessible for training. In this work, we proposed a model that takes time-series customers’ electric kickboard demand data as input, pre-processes it, and generates synthetic data according to the original data distribution using generative adversarial networks (GAN). The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data. We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results. We modified The Wasserstein GAN-gradient penalty (GP) with the RMSprop optimizer and then employed Spectral Normalization (SN) to improve training stability and faster convergence. Finally, we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction. We used various evaluation criteria and visual representations to compare our proposed model’s performance. Synthetic data generated by our suggested GAN model is also evaluated. The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem, and it also converges faster than previous GAN models for synthetic data creation. The presented model’s performance is compared to existing ensemble and baseline models. The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error (MAPE) of 4.476 and increase prediction accuracy.