Fusion: Practice and Applications FPA 2692-4048 2770-0070 10.54216/FPA https://www.americaspg.com/journals/show/1708 2018 2018 Computer Communication Department, Al Rafidain University College, Baghdad, Iraq Talib A. Al Al-Sharify Department of computer engineering techniques, Mazaya University college, Thi Qar, Iraq Mohammed Hussein .. Department oof medical instrument engineering techniques, Alfarahidi University, Baghdad, Iraq Aqeel Hussen Radiological Techniques Department, Al- Mustaqbal University College, 51001 Hilla, Iraq Zaid Saad Madhi With the use of multi-level features fusion, this work provides a new method for recognizing cognitive brain activity, which we term the Improved Multi-modal cognitive brain-imaging method (IMCBI). Identifying brain areas and basing judgments on insights into intelligent cognitive behavior for babies and adolescents presents a number of methodological issues that the suggested approach seeks to address. In order to understand how the brain functions during various motor, perceptual, and cognitive tasks, IMCBI employs smart methods for fusing data at several levels. This technique employs functional magnetic resonance imaging (fMRI) data to assess human behavioral activity in the brain while engaging in a variety of activities. It does so by combining an inter-subject retrieval strategy with deep neural networks (DNN). The research shows that the suggested method, which uses multi-level fusion of features, greatly raises the accuracy ratio to 95.63 percent, the sensitivity to 95.42 percent, and the specificity to 94.3 three point three percent. The findings demonstrate the method's efficacy in recognizing brain activity based on high-level cognitive ability, making it a useful tool for predicting clinical and behavioral responses. 2023 2023 100 113 10.54216/FPA.110108 https://www.americaspg.com/articleinfo/3/show/1708