As the silicon material is severely influenced by the ambient temperature, the silicon piezo-resistive pressure sensor remarkably suffers from a strong nonlinearity in the response characteristic as the ambient temperature varies. To address this crucial issue, an adaptive mutation particle swarm optimization optimized support vector regression (AMPSO-SVR) combined with improved AdaBoost.RT algorithm is presented. The opposition-based learning initialization and Levy mutation is applied in the adaptive mutation particle swarm optimization (AMPSO) to achieve the appropriate model selection task which directly determines the performance of SVR. The performance of original AdaBoost.RT is improved by a dynamical modification approach for threshold and quoted error criterion. In order to verify the effectiveness of the proposed temperature compensation approach, several additional optimization methods such as Cuckoo search (CS), dragonfly algorithm (DA), multi-verse optimizer (MVO), conventional particle swarm optimization (PSO), Levy flight improved particle swarm optimization (Levy-PSO) and the AMPSO combined with SVR are investigated. The minimum quoted error, maximum quoted error, the mean quoted error and the variance of the quoted error over testing data obtained by the proposed method are $6.8764\times 10^{-5}$ , $6.4463\times 10^{-4}$ , $3.2619\times 10^{-{4}}$ and $2.5714\times 10^{-8}$ respectively, which are superior to the corresponding indices obtained by other methods. The analysis of simulation results indicates the method proposed in this research is applicable, effective and efficient for industrial application.