Long non-coding RNA (IncRNA) play critical roles in the occurrence and development of various diseases. The determination of the IncRNA-disease associations thus would contribute to provide new insights into the pathogenesis of the disease, the diagnosis, and the gene treatments. Considering that traditional experimental approaches are difficult to detect potential human IncRNA-disease associations from the vast amount of biological data, developing computational method could be of significantvalue. In this paper, we proposed a novel computational method named LDASR to identify associations between IncRNA and disease by analyzing known IncRNA-disease associations. First, the feature vectors of the IncRNA-disease pairs were obtained by integrating IncRNA Gaussian interaction profile kernel similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity. Second, autoencoder neural network was employed to reduce the feature dimension and get the optimal feature subspace from the original feature set. Finally, Rotating Forest was used to carry out prediction of IncRNA-disease association. The proposed method achieves an excellent preference with 0.9502 AUC in leave-one-out cross-validations (LOOCV) and 0.9428 AUC in 5-fold cross-validation, which significantly outperformed previous methods. Moreover, two kinds of case studies on identifying IncRNAs associated with colorectal cancer and glioma further proves the capability of LDASR in identifying novel IncRNA-disease associations. The promising experimental results show that the LDASR can be an excellent addition to the biomedical research in the future.