Human factors have an important impact on aviation safety. The evaluation of pilot's workload is one of the most noteworthy human factor issues. In this paper, we introduce an efficient algorithm for finding the effective sparse feature Principal Component (PC) of multiple physiological signals. Sparse Principal Component Analysis (SPCA) imposes extra constraints or penalty terms to the standard Principal Component Analysis (PCA) to achieve sparsity. Experiments on multiple physiological signals datasets from flight task show that SPCA is faster than PCA, especially on large and sparse data sets, while the numerical quality of the solution is comparable to PCA algorithm and the principal components extracted by SPCA are easier to explain.