Exploring the Machine Learning (ML) features and methods based on electroencephalography (EEG) and quantitative electroencephalographic (qEEG) holds the potential to early diagnosis and classification of Parkinson’s disease (PD) and can bring convenience to the decision-making process for healthcare professionals. PD is clinically heterogeneous, with high variability between patients in terms of motor and non-motor symptoms. This nature makes it extremely challenging for early diagnosis, and severity classification using traditionally questionnaire-based standards. EEG and qEEG provide objective signals with rich features that can potentially provide a translational alternative. In the past decade, a host of ML-based features and algorithms have been developed to detect and classify PD in patients using a range of EEG and qEEG datasets. Various methodologies, including graph-CNNs, deep RNNs, and hybrid models, are discussed within the context of early diagnosis and classification, each offering unique insights and performance levels. This review highlights the multifaceted nature of PD diagnosis and classification research. It addresses the challenges and limitations encountered in existing techniques, emphasizing the need for further improvements in accuracy, sensitivity, and specificity. This review provides a standardized insight into the evolving landscape of PD diagnosis and classification. It showcases the remarkable progress that has been made in utilizing EEG and qEEG data while emphasizing the ongoing quest for effective and convenient ML based methods for early diagnosis and classification.

The optimal stiffnesses and spatial locations of contact-aided compliant mechanisms in a dynamic flapping wing structure are found using a numerical dynamics model and multi-objective genetic algorithm. Using mathematical descriptions of how wing shape change impact pitch agility in a flapping wing mechanical bird, an optimization problem was formulated to find compliant joint stiffness and location parameters which induce desired shape change. Specifically, the goal of the shape change was to induce forward sweep at the upstroke to downstroke transition while otherwise remaining stiff in an effort to move the aerodynamic center ahead of the center of gravity. A single compliant joint in the leading edge spar of an ornithopter wing was considered. A multi-objective genetic algorithm was used to solve the optimization problem, generating 3892 unique designs over 20 generations. Machine learning visualization and regression was used to better understand the data set. The data set was narrowed using higher level decisions, and one optimal design which satisfied the design requirements was chosen based on its relative performance and design parameters. The design was able to achieve the desired forward sweep while only allowing small bending and twist motion compared to the wing structure without a compliant joint inserted.