The early detection of Alzheimer's disease (AD) is crucial for effective intervention and management. This study aims to detect AD using electroencephalogram (EEG) signals analyzed through advanced machine learning techniques. The dataset, provided by researchers from Florida State University, consists of EEG recordings from 24 healthy controls and 24 patients diagnosed with AD using a 19-electrode recorder in accordance with the international 10–20 system. The recordings were captured using the Biologic Systems Brain Atlas III Plus workstation. EEG signals were preprocessed to remove noise and artifacts, and features were extracted using a finite impulse response (FIR) filter in the double-time domain, focusing on changes in the power spectrum associated with AD. These features were then used to train and test three machine learning classifiers: the support vector machine (SVM), naive Bayes, and XGBoost. Among these, the XGBoost model demonstrated the highest accuracy, achieving a remarkable 96% accuracy in distinguishing between AD patients and healthy controls. The superior performance of the XGBoost model underscores the potential of EEG signal analysis combined with machine learning for the early detection of Alzheimer's disease. This approach provides a non-invasive and cost-effective diagnostic tool and offers significant promise for improving the timely diagnosis and management of AD. This study highlights the efficacy of leveraging advanced signal processing and machine learning techniques in the field of neurodiagnostics, paving the way for innovative solutions in the detection and monitoring of neurodegenerative diseases.