Figure 1 elucidates several interesting points.
Third, Python scripts used Scopus Application Programming Interfaces (APIs) to identify the number of scientific publications that matched sets of ML and division symposia keywords. Second, lists of keywords were created by perusing ACS division symposia titles from over the past five years. Preparing this figure required several steps. Specifically, we wanted to review why and how CompChem+ML can provide useful insights into the study of molecules and materials.Īs context for this Review, Figure 1 shows a heatmap depicting the frequency of ML keywords found in scientific articles that also have keywords associated with different American Chemical Society (ACS) technical divisions. From this, we see a need for researchers working at the intersection of CompChem+ML to more critically recognize the true strengths and weaknesses of each component in any given study. (20) At the same time, we have witnessed hype, criticism, and misunderstanding about how ML tools are to be used in chemical research. (17−19) These methods have also become popular for accelerating the discovery and design of new materials, chemicals, and chemical processes. (1−3) Applications of ML include technological fields, such as web search, translation, natural language processing, self-driving vehicles, control architectures, and in the sciences, for example, medical diagnostics, (4−8) particle physics, (9) nano sciences, (10) bioinformatics, (11,12) brain-computer interfaces, (13) social media analysis, (14) robotics, (15,16) and team, social, or board games.
The predicted Arrhenius constant and activation energy values were respectively 2.54 × 10 -11 m 2/s and 21.65 kJ/mol.Machine learning (ML) methods have in the past decades witnessed an unprecedented technological evolution enabling a plethora of applications, some of which have become daily companions in our lives. The obtained moisture diffusivity values were 2.73496 and 1.82331 × 10 -11 m 2/s for the solar drying of locust beans under forced and natural convection mode respectively. Thus, this model may be adjudged to represent the drying characteristics of locust beans in a thin layer within the experimental range of study. The results showed that the Lewis model gave the best description of solar drying of locust beans under forced and natural convection mode.
The experimental data obtained were fitted into eleven existing thin layer models and the best model choice was based on a comparison of statistical parameters including determination coefficient (R 2), reduced chi-square (ᵪ 2), root mean square error (RMSE), square error sum (SSE) and normalised root mean square error (NRMSE) between the experimental and predicted data. This study investigated the modelling of moisture diffusivity of processed locust beans under forced and natural convection mode using solar drying with thermal storage materials (gravel).
0 kommentar(er)
