Search

Parkinson's disease, a debilitating neurological disorder affecting mobility, stands as one of the most prevalent and life-altering conditions within the realm of neurological disorders. Tragically, it currently lacks a definitive cure, significantly impacting life expectancy and resulting in substantial disabilities. Recognizing and diagnosing the condition early is paramount to mitigating its effects. Notably, more than 90% of individuals afflicted by Parkinson's experience speech impairments. This underscores the significance of speech features in the diagnostic process. To streamline and improve the accuracy of Parkinson's diagnosis, this study employs an automated diagnostic process. It leverages ensemble methods, integrating feature selection techniques, and implements the Extremely Randomized Trees (ERT) classifier based on voice characteristics. Through rigorous experimentation, the effectiveness of the ERT classifier is assessed using various feature selection methods. Notably, when combined with embedded LASSO, the ERT classifier achieves an impressive accuracy of 87%. This substantial improvement in diagnostic accuracy has far-reaching implications for early detection and management of Parkinson's disease. By providing clinicians and healthcare professionals with a reliable, non-invasive, and cost-effective screening tool, this approach promises to significantly enhance the quality of life for patients battling this debilitating condition. [ABSTRACT FROM AUTHOR]

In recent years, localizing or identifying the position of unknown sensor nodes has become an essential problem in Wireless Sensor Networks (WSN). The improvement in localization accuracy leads to obtaining the exact location of the dumb node. Among all localization algorithms, Amorphous localization is highly suggested for usage in many application domains due to its simplicity, viability, low cost, and zero additional hardware requirements. Position estimation of the dumb node in the Amorphous algorithm considers three different practical scenarios, such as the position of dumb nodes falling within the range of anchor nodes, the position of the dumb node being in the opposite direction of the anchor node, and the position of the dumb node not within the range of anchor node. However, the localization error generated by the Amorphous algorithm is high. To address the limitations of Amorphous algorithm we have proposed a PSO based Amorphous algorithm. The proposed work reduces the average hop size of anchor nodes and reduces the localization error. The simulation results demonstrate that, in comparison to other existing Amorphous algorithms, the proposed PSO based Amorphous localization algorithm produced a superior performance in terms of MAE, MSE and RMSE. [ABSTRACT FROM AUTHOR]