Enhanced wave overtopping simulation at vertical breakwaters using machine learning algorithms

Accurate prediction of wave overtopping at sea defences remains central to the protection of lives, livelihoods, and infrastructural assets in coastal zones. In addressing the increased risks of rising sea levels and more frequent storm surges, robust assessment and prediction methods for overtopping prediction are increasingly important. Methods for predicting overtopping have typically relied on empirical relations based on physical modelling and numerical simulation data. In recent years, with advances in computational efficiency, data-driven techniques including advanced Machine Learning (ML) methods have become more readily applicable. However, the methodological appropriateness and performance evaluation of ML techniques for predicting wave overtopping at vertical seawalls has not been extensively studied. This study examines the predictive performance of four ML techniques, namely Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Support Vector Machines-Regression (SVR), and Artificial Neural Network (ANN) for overtopping discharge at vertical seawalls. The ML models are developed using data from the EurOtop (2018) database. Hyperparameter tuning is performed to curtail algorithms to the intrinsic features of the dataset. Feature Transformation and advanced Feature Selection methods are adopted to reduce data redundancy and overfitting. Comprehensive statistical analysis shows superior performance of the RF method, followed in turn by the GBDT, SVR, and ANN models, respectively. In addition to this, Decision Tree (DT) based methods such as GBDT and RF are shown to be more computationally efficient than SVR and ANN, with GBDT performing simulations more rapidly that other methods. This study shows that ML approaches can be adopted as a reliable and computationally effective method for evaluating wave overtopping at vertical seawalls across a wide range of hydrodynamic and structural conditions.

Herbal Medicine: Clinical Perspective and Regulatory Status

Herbal medicines play an important role in treating various ailments due to their potentially high therapeutic values and acceptability by patients with different health complications. The practice of herbal medicine involves the use of a part of a plant, the entire plant, or a selective isolated phytoconstituent. The search for new drugs during the scientific era revived the interest in the discovery of herbal drugs from different natural resources. The present modern healthcare system involves the utilization of drugs and 50% of them are of natural origin. In recent years, there had been an upsurge in the interest for search of novel herbal drugs by the pharmaceutical industry. However, the discovery of such new novel phytomedicines involves various challenges in the identification of active constituents; their characterization, pharmacological activity, toxicity/adverse effects, drug interactions, and, most importantly, their regulatory requirements. The present review is mainly focused on the history of herbal medicine, current clinical perspective, and pharmaceutical and regulatory challenges facing herbal drugs. Moreover, problems encountered in drug discovery from herbal resources and their possible solutions have been delineated.

Electrospun PVDF-TrFE/MXene Nanofiber Mat-Based Triboelectric Nanogenerator for Smart Home Appliances

Understanding of the triboelectric charge accumulation from the view of microcapacitor formation plays a critical role in boosting the output performance of the triboelectric nanogenerator (TENG). Here, an electrospun nanofiber-based TENG (EN-TENG) using a poly(vinylidene fluoride-trifluoroethylene) (PVDF-TrFE)/MXene nanocomposite material with superior dielectric constant and high surface charge density is reported. The influence of dielectric properties on the output performance of the EN-TENG is investigated theoretically and experimentally. The fabricated EN-TENG exhibited a maximum power density of 4.02 W/m² at a matching external load resistance of 4 MΩ. The PVDF-TrFE/MXene nanocomposite improved the output performance of the EN-TENG fourfold. The EN-TENG successfully powered an electronic stopwatch and thermo-hygrometer by harvesting energy from human finger tapping. Moreover, it was utilized in smart home applications as a self-powered switch for controlling electrical home appliances, including fire alarms, fans, and smart doors. This work presents an effective and innovative approach toward self-powered systems, human-machine interfaces, and smart home applications.