Search

Accurate automobile-demand forecasting can provide effective guidance for automobile-manufacturing enterprises in terms of production planning and supply planning. However, automobile sales volume is affected by historical sales volume and other external factors, and it shows strong non-stationarity, nonlinearity, autocorrelation and other complex characteristics. It is difficult to accurately forecast sales volume using traditional models. To solve this problem, a forecasting model combining trend extrapolation and causality analysis is proposed and derived from the historical predictors of sales volume and the influence of external factors. In the trend-extrapolation model, the historical predictors of sales series was captured based on the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Polynomial Regression (PR); then, Empirical Mode Decomposition (EMD), a stationarity-test algorithm, and an autocorrelation-test algorithm were introduced to reconstruct the sales sequence into stationary components with strong seasonality and trend components, which reduced the influences of non-stationarity and nonlinearity on the modeling. In the causality-analysis submodel, 31-dimensional feature data were extracted from influencing factors, such as date, macroeconomy, and promotion activities, and a Gradient-Boosting Decision Tree (GBDT) was used to establish the mapping between influencing factors and future sales because of its excellent ability to fit nonlinear relationships. Finally, the forecasting performance of three combination strategies, namely the boosting series, stacking parallel and weighted-average parallel strategies, were tested. Comparative experiments on three groups of sales data showed that the weighted-average parallel combination strategy had the best performance, with loss reductions of 16.81% and 4.68% for data from the number-one brand, 25.60% and 2.79% for data from the number-two brand, and 46.26% and 14.37% for data from the number-three brand compared with the other combination strategies. Other ablation studies and comparative experiments with six basic models proved the effectiveness and superiority of the proposed model. [ABSTRACT FROM AUTHOR]

The appearance of tea leaves is the most intuitive factor in assessing their quality and is an important indicator of the price. The study utilizes machine vision and hyperspectral image technology to develop a rapid method for assessing the appearance quality of seven grades of Dianhong Congou black tea samples based on shape, color, texture, and feature fusion. Using the shape metrics of length, width, perimeter, narrowness, area, and rectangularity, 88 texture values, and nine color values as features, the effectiveness of intelligent recognition algorithms such as support vector machine, random forest, and least squares support vector machine (LSSVM) in classifying single features (shape, color, and texture) and fused data models of the categories of Dianhong tea samples was explored. The results showed that the accuracy of the feature fusion-based appearance quality evaluation models was all higher than the modeling results of the corresponding single features, and the accuracy of the LSSVM model based on the fused data was 100%. This study showed that feature data fusion reflects the external information of tea leaves more comprehensively and that intelligent classification algorithms combined with image analysis techniques were an effective strategy for the identification of regional black tea. [ABSTRACT FROM AUTHOR]