The procedure of computer-aided diagnosis for Alzheimer’s disease forecast has gotten better using deep learning principles. Such techniques rely on deep spatial features for classification. Nevertheless, the systems’ capabilities have to be enhanced. Furthermore, deep-frequency domain characteristics for Alzheimer’s diagnosis are understudied. This article fills the said research gaps by exploiting deep frequency features for disease prediction. The model utilizes the high-level and low-level frequency-based DWT features. Then a two-stream deep CNN architecture is designed where the low- and high-level frequency components are inputted. Each stream is a multi-layer of conventional CNN layers. Concatenation of the deep characteristics of the two streams is performed, and then the information is sent to a multi-layer of dense layers for illness classification. Achievement of the suggested model is evaluated by experimenting on OASIS and the Kaggle AD datasets and the obtained results outperform the existing state-of-the-arts.