Table 1 FSVR-AD Algorithm.
From: Logistics demand prediction using fuzzy support vector regression machine based on Adam optimization
Input: sample set \(\left({x}_{i},{y}_{i}\right),\) \(\left({x}_{i},{y}_{i}\right)\in {R}^{n}\times R,i=\mathrm{1,2},\,\cdot \cdot \cdot\,,m,\) penalty parameter \(C=100\). |
â‘ Compute the \({x}_{R}=\frac{{\sum }_{i=1}^{m}{x}_{i}}{m}\), \(D({x}_{i})=\Vert {x}_{i}-{x}_{R}\Vert\) and \(R=\frac{{\sum }_{i=1}^{m}D({x}_{i})}{m}\). |
â‘¡Compute \({\omega }_{1i}\) and \({\omega }_{2i}\) according to the formula (2.9) and (2.10), respectively. |
â‘¢Compute the fuzzy membership according to formula \({S}_{i}=\lambda {\omega }_{1i}+\mu {\omega }_{2i}\). |
â‘£Using the Adam optimization algorithm to optimize the formula (2.12), and obtain the optimal values of the weight vector \({w}^{* }\) and bias \({b}^{* }\). |
Output: the optimal weight vector \({w}^{* }\) and optimal bias \({b}^{* }\), the decision function \(f\left(x\right)={w}^{* }x+{b}^{* },\) the prediction values of the FSVR-AD for input data. |
