<abstract><p>This research paper introduces a portfolio recommendation system that utilizes machine learning and big data analytics to offer a profitable stock portfolio and stock analytics via a web application. The system's effectiveness was evaluated through backtesting and user evaluation studies, which consisted of two parts: user evaluation and performance evaluation. The findings indicate that the development of a machine learning-based portfolio recommendation system and big data analytics can effectively meet the expectations of the majority of users and enhance users' financial knowledge. This study contributes to the growing body of research on utilizing advanced technologies for portfolio recommendation and highlights the potential of machine learning and big data analytics in the financial industry.</p></abstract>
Rapid sintering is one of the most attractive metalworking technologies due to its ability to fabricate the final product with different microstructure in an economical manner. During this process, the high heating rate would induce a great thermal gradient to the sintering part. Such temperature differences affect the microstructure of the product, which in turn leads to the occurrence of microstructure defects. However, for this non-isothermal sintering, the present Radiative Transfer Equation approach or Units/Cells approach cannot effectively compute the temperature distributions inside the porous media, so as to predict the part defects. Cumbersome computations are needed for the Radiative Transfer Equation approach. For the Units/Cells approach, the use of regular assembly in the model limits the analysis of complex packed sphere systems. This study seeks to simplify the entire computational process for different packed sphere systems. By introducing a Radiative Transfer Coefficient (RTC) approach, the computation of radiative heat transfer within the porous bed can be enhanced. The newly introduced Radiative Transfer Coefficient is defined as the ratio of radiative energy exchange, including direct and indirect exchange, from the emitting sphere to the receiving sphere, which is a function of the system microstructure and radiative properties. A set of energy-balanced algebraic equations can then be established. With an appropriate initial energy guess for each sphere, these equations can be solved by the Gauss-Seidel iteration scheme, thereby computing the radiative heat transfer in packed sphere systems with different microstructures and radiative properties. The temperature for each sphere can therefore be computed right away. This model has been validated in different perspectives. With this RTC approach, the overall computational time required is significantly shorter, providing a set of fine-resolution temperature solution.
Sintering is a thermally activated solid diffusion process. Study of the heat transfer process is one of the key elements for the improvement of sintering technology. Within sphere packings, the three-dimensional interconnected network of spheres and the interconnected pore structures are very complex. In order to bypass this complexity, typically, the porous medium approach has been used for applications allow relative coarse resolution. However, for sintering studies, the traditional effective conductivity determination may not be directly applicable. Firstly, the porosity variation may be very rigorous due to the non-uniform densification process with a stiff temperature gradient. Furthermore, a fine control volume is required for the fine temperature resolution for studying the effect on unbalance densification rate within packings. Therefore, it is necessary to investigate the dependence of the effective conductivity of the small packing on the detailed packing parameters, such as coordination number and the contact radius ratio. Indeed, this study was one of the first attempts to investigate such effect. A numerical study was performed. The results showed that porosity is indeed not the unique parameter for describing the packing structure while the mean coordination number and the mean contact radius ratio are more appropriate for small population size of spheres. With the developed correlation, the effective conductivity can be directly determined for any packing with the known mean coordination number and the known contact radius ratio without requiring any empirical determination.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.