Enhancing Parkinson’s Disease Diagnosis Accuracy Through Speech Signal Algorithm Modeling

Parkinson’s disease (PD), one of whose symptoms is dysphonia, is a prevalent neurodegenerative disease. The use of outdated diagnosis techniques, which yield inaccurate and unreliable results, continues to represent an obstacle in early-stage detection and diagnosis for clinical professionals in the medical field. To solve this issue, the study proposes using machine learning and deep learning models to analyze processed speech signals of patients’ voice recordings. Datasets of these processed speech signals were obtained and experimented on by random forest and logistic regression classifiers. Results were highly successful, with 90% accuracy produced by the random forest classifier and 81.5% by the logistic regression classifier. Furthermore, a deep neural network was implemented to investigate if such variation in method could add to the findings. It proved to be effective, as the neural network yielded an accuracy of nearly 92%. Such results suggest that it is possible to accurately diagnose early-stage PD through merely testing patients’ voices. This research calls for a revolutionary diagnostic approach in decision support systems, and is the first step in a market-wide implementation of healthcare software dedicated to the aid of clinicians in early diagnosis of PD.     

Inclined Physical Subsurface Barriers for Saltwater Intrusion Management in Coastal Aquifers

Saltwater intrusion (SWI) has a negative environmental impact on groundwater quality in coastal areas. Therefore, effective management strategies are required to preserve fresh groundwater resources. Historically, vertical barriers have been exclusively considered in both numerical studies and practical applications. The novelty of this study consists in investigating the SWI mitigation effectiveness of inclined physical subsurface barriers (PSBs), and specifically cutoff walls (CWs) and subsurface dams (SDs). An initial benchmark analysis of the Henry problem was performed. Following verification, the proposed model was applied to a real case study - the Biscayne aquifer (Southeastern Florida, USA). The model simulations run for different scenarios considering the vertical placement of the PSB, an inclined placement of the PSB according to different slopes (1/4, 1/2 and 1/1, at sea- and landside) and the combination of the best scenario. The results showed that CWs are more effective in limiting SWI in comparison with SDs. The most positive impact in both cases was achieved for a slope of 1/4, indicating that a moderate vertical inclination of the PSB better preserve coastal groundwater resources. The model presented in this work can be a valuable tool for policy makers in predicting the coastal aquifer response. However, a comprehensive cost–benefit analysis is required to further account for the feasibility and the economic costs related to the construction of inclined PSBs.