e., word embeddings as a semantic text representation) as input features. We resorted to nested 10-fold cross-validation to evaluate the performance of competing methods using accuracy, precision, recall, and F 1 score. The CNN with semantic word representations as input yielded the overall best performance, having a micro-averaged F 1 score of 86 . 7 % . The CNN classifier yielded particularly encouraging results for the most represented conditions degenerative disease ( 95 . 9 % ), arthrosis ( 93 . 3 % ), and injury ( 89 . 2 % ). As a data-hungry deep learning model, the CNN, however, performed notably worse than the competing models on underrepresented classes with fewer training instances such as multicausal disease or metabolic disease. LR, RF, and SVM performed comparably well, with the obtained micro-averaged F 1 scores of 84 . 6 % , 82 . 2 % , and 82 . 1 % , respectively.The treatment options for a patient diagnosed with Alzheimer’s disease (AD) are currently limited. The cerebral accumulation of amyloid-β (Aβ) is a critical molecular event in the pathogenesis of AD. When the amyloidogenic β-secretase (BACE1) is inhibited, the production of Aβ peptide is reduced. Henceforth, the main goal of this study is the discovery of new small bioactive molecules that potentially reach the brain and inhibit BACE1. The work was conducted by a customized molecular modelling protocol, including pharmacophore-based and molecular docking-based virtual screening (VS). Structure-based (SB) and ligand-based (LB) pharmacophore models were designed to accurately screen several drug-like compound databases. The retrieved hits were subjected to molecular docking and in silico filtered to predict their ability to cross the blood-brain barrier (BBB). Additionally, 34 high-scoring compounds structurally distinct from known BACE1 inhibitors were selected for in vitro screening assay, which resulted in 13 novel hit-compounds for this relevant therapeutic target. This study disclosed new BACE1 inhibitors, proving the utility of combining computational and in vitro approaches for effectively predicting anti-BACE1 agents in the early drug discovery process.Postmenopausal women experiencing health transitions can improve health-related quality of life through clinical health service use. The aim of this study was to investigate the factors affecting clinical preventive service use, focusing on a multi-dimensional approach among middle-aged postmenopausal women. This descriptive study is a secondary analysis of the seventh Korea National Health and Nutrition Examination Survey (KNHANESⅦ-1) in 2016. Among the 8150 participants, our analysis included 771 naturally menopausal women aged 40-65. National health insurance (OR = 1.659, 95% CI = 1.080-2.550), private health insurance (OR = 2.877, 95% CI = 1.665-4.971), needs for health service (OR = 2.363, 95% CI = 1.332-4.195), cardiovascular disease (OR = 1.570, 95% CI = 1.009-2.445), hospital admission (OR = 3.054, 95% CI = 1.298-7.184), smoking (OR = 0.262, 95% CI = 0.144-0.477), drinking (OR = 0.573, 95% CI = 0.335-0.979), and depression (OR = 0.535, 95% CI = 0.340-0.841) were associated with clinical preventive service use among middle-aged postmenopausal women. To promote clinical preventive service use among postmenopausal women, policies promoting health behavior expansion should be introduced and should consider the predictive variables revealed by this study.This paper focuses on the light transmittance of macroporous silica as a photocatalyst carrier. In addition to the characteristics of photocatalysts, the structure of porous bulk is also important since it affects the propagation of light. Realistic porous structures are generated by a Voronoi-based approach. Four morphological parameters are highly controlled during generating, that is, porosity, coefficient of variation, diameter ratio and normalized curvature. Finite element method (FEM) is used to simulate the propagation of light in the porous models in the visible light range. The intensity shows a quadratic decrease with the increase of the depth of light propagation. check details The influences of the morphological parameters on the light transmittance are analysed. It turns out that the porosity has a great influence on the light transmittance while the coefficient of variation and the diameter ratio have small ones. Moreover, the influence of the normalized curvature is little. Besides, the effect of the wavelength of visible light can not be ignored. With the simulation, the depth of visible light entering the porous silica can be estimated, which is challenging to access experimentally.Structural dynamic modeling is a key element in the analysis of building behavior for different environmental factors. Having this in mind, the authors propose a simple nonlinear model for studying the behavior of buildings in the case of earthquakes. Structural analysis is a key component of seismic design and evaluation. It began more than 100 years ago when seismic regulations adopted static analyzes with lateral loads of about 10% of the weight of the structure. Due to the dynamics and non-linear response of the structures, advanced analytical procedures were implemented over time. The authors’ approach is the following having a nonlinear dynamic model (in this case, a multi-segment inverted pendulum on a cart with mass-spring-damper rotational joints) and at least two datasets of a building, the parameters of the building’s model are estimated using optimization algorithms Particle Swarm Optimization (PSO) and Differential Evolution (DE). Not having much expertise on structural modeling, the present paper is focused on two aspects the proposed model’s performance and the optimization algorithms performance. Results show that among these algorithms, the DE algorithm outperformed its counterpart in most situations. As for the model, the results show us that it performs well in prediction scenarios.Quadcopters are beginning to play an important role in precision agriculture. In order to localize and operate the quadcopter automatically in complex agricultural settings, such as a greenhouse, a robust positioning system is needed. In previous research, we developed a spread spectrum sound-based local positioning system (SSSLPS) with a 20 mm accuracy within a 30 × 30 m greenhouse area. In this research, a noise tolerant SSSLPS was developed and evaluated. First, the acoustic noise spectrum emitted by the quadcopter was documented, and then the noise tolerance properties of SSSounds were examined and tested. This was done in a greenhouse with a fixed quadcopter (9.75 N thrust) with the positioning system mounted on it. The recorded quadcopter noise had a broadband noise compared to the SSSound. Taking these SSSound properties into account, the noise tolerance of the SSSLPS was improved, achieving a positioning accuracy of 23.2 mm and 31.6 mm accuracy within 12 × 6 m for both Time-division Multiple Access (TDMA) and Frequency-division Multiple Access (FDMA) modulation.