The identification of new probiotics with anti-obesity properties has attracted considerable interest. In the present study, the anti-obesity activities of
(
) strains isolated from human stool ...samples and their relationship with the gut microbiota were evaluated using a high fat-diet (HFD)-fed mice model. Three strains of
were chosen from 27 isolates selected based on their anti-lipogenic activity in 3T3-L1 cells. The anti-lipogenic, anti-adipogenic and anti-obesity properties of these three strains were evaluated further in HFD-induced obese mice. The animals were administered these strains six times per week for 12 weeks. The treatment improved the HFD-induced metabolic disorders in mice in terms of the prevention of body weight gain, caloric intake and reduction in the weights of the major adipose tissues and total fat. In addition, it improved glucose homeostasis and insulin sensitivity. These effects were also associated with the inhibition of low-grade intestinal inflammation and restoration of damaged gut integrity, prevention of liver steatosis and improvement of hepatic function. These results revealed a difference in the distribution pattern of the gut microbial communities between groups. Therefore, the gut microbial population modulation, at least in part, might contribute to the beneficial impact of the selected
strains against metabolic disorders.
•Recent advances in deep learning and reinforcement learning (RL) are reviewed.•Motivation, early problems and recent resolutions of deep learning are discussed.•The idea of RL and its success in the ...Go game (a la AlphaGo) are introduced.•Applicability of RL to multi-stage decision problems in industries is discussed.•Potential applications and research directions of ML in the PSE domains are given.
Machine learning (ML) has recently gained in popularity, spurred by well-publicized advances like deep learning and widespread commercial interest in big data analytics. Despite the enthusiasm, some renowned experts of the field have expressed skepticism, which is justifiable given the disappointment with the previous wave of neural networks and other AI techniques. On the other hand, new fundamental advances like the ability to train neural networks with a large number of layers for hierarchical feature learning may present significant new technological and commercial opportunities. This paper critically examines the main advances in deep learning. In addition, connections with another ML branch of reinforcement learning are elucidated and its role in control and decision problems is discussed. Implications of these advances for the fields of process and energy systems engineering are also discussed.
•The high-level planning is formulated as a Markov decision process (MDP).•The low-level operation model is constructed as a mathematical programming (MP).•MDP and MP are combined in a complementary ...way for integrating the decision layers.•Reinforcement learning is introduced to solve the MP-embedded MDP problem.•A benchmark case study of refinery is presented to illustrate the proposed method.
This study focuses on the linkage between decision layers that have different time scales. The resulting expansion of the boundary of decision-making process can provide more robust and flexible management and operation strategies by resolving inconsistencies between different levels. For this, we develop a multi-timescale decision-making model that combines Markov decision process (MDP) and mathematical programming (MP) in a complementary way and introduce a computationally tractable solution algorithm based on reinforcement learning (RL) to solve the MP-embedded MDP problem. To support the integration of the decision hierarchy, a data-driven uncertainty prediction model is suggested which is valid across all time scales considered. A practical example of refinery procurement and production planning is presented to illustrate the proposed method, along with numerical results of a benchmark case study.
This paper provides an introduction to Reinforcement Learning (RL) technology, summarizes recent developments in this area, and discusses their potential implications for the field of process ...control, and more generally, of operational decision-making. The paper begins with an introduction to RL that allows an agent to learn, through trial and error, the best way to accomplish a task. We then highlight new developments in RL that have led to the recent wave of applications and media interest. A comparison of the key features of RL and mathematical programming based methods (e.g., model predictive control) is then presented to clarify their similarities and differences. This is followed by an assessment of several ways that RL technology can potentially be used in process control and operational decision applications. A final section summarizes our conclusions and lists directions for future RL research that may improve its relevance for the process systems engineering field.
•A microgrid is managed by considering dynamic and uncertain nature of the system.•2SSP for a day operation is combined with a day-to-day MDP for temporal connection.•Size of the system component is ...optimized based on the value function for the MDP.•A multi-scale wind model is developed for integration of the decision hierarchy.•The proposed method is examined for a benchmark case study with real wind data.
Distributed and on-site energy generation and distribution systems employing renewable energy sources and energy storage devices (referred to as microgrids) have been proposed as a new design approach to meet our energy needs more reliably and with lower carbon footprint. Management of such a system is a multi-scale decision-making problem encompassing hourly dispatch, daily unit commitment (UC), and yearly sizing for which efficient formulations and solution algorithms are lacking thus far. Its dynamic nature and high uncertainty are additional factors in limiting efficient and reliable operation. In this study, two-stage stochastic programming (2SSP) for day-ahead UC and dispatch decisions is combined with a Markov decision process (MDP) evolving at a daily timescale. The one-day operation model is integrated with the MDP by using the value of a state of commitment and battery at the end of a day to ensure longer term implications of the decisions within the day are considered. In the MDP formulation, capturing daily evolving exogenous information, the value function is recursively approximated with sampled observations estimated from the daily 2SSP model. With this value function capturing all future operating costs, optimal sizing of the wind farm and battery devices is determined based on a surrogate function optimization. Meanwhile, a multi-scale wind model consistent from seasonal to hourly is developed for the connection of the decision hierarchy across the scales. The results of the proposed integrated approach are compared to those of the daily independent 2SSP model through a case study and real wind data.
This study investigated the impact of increased depressive feelings during the COVID-19 pandemic on the suicidal behavior of Korean high school students using the 17th Korea Youth Risk Behavior ...Web-Based Survey (KYRBS). We classified the independent variables into four groups ("no depressive mood and no increase in depressive feelings group A", "no depressive mood and increase in depressive feelings group B", "depressive mood and no increase in depressive feelings group C", and "depressive mood and increase in depressive feelings group D"). Compared to group A, group D showed an odds ratio of 18.30 in men and 14.87 in women for suicidal behavior after accounting for demographic and health behavioral characteristics. We found that depressive mood and a relatively short-term increase in depressive feelings had a synergistic effect, rather than an additive one, on suicidal behavior. Based on this result, we claim that an appropriate intervention method is necessary to prevent adolescents' depressive mood from developing into suicidal behavior during the pandemic.
•Crude oil is classified into five types based on the viscosity index (VI) of VGO.•Prediction models for the yield and VI in lube hydro-processing are developed.•The lube processing model is ...incorporated in the overall refinery optimization.•Case studies with several price scenarios and sensitivity analysis are conducted.•Benefits of the model-based optimization method in lube refinery are illustrated.
An optimization-based strategy is developed for crude selection in a refinery with lube base oil (LBO) producing capability. Crude oil is classified into five types based on the viscosity index (VI) and the compositional aspect of vacuum gas oil (VGO). A prediction model for the VI, the most important quality variable in LBO processing, is developed for VGO based on its bulk properties. For each crude type, prediction models for the yield and the VI change vs. the conversion rate during lube hydro-processing are developed. The lube hydro-processing models are then incorporated into the overall refinery optimization to maximize the overall margin while satisfying all the specifications of the lube and fuel products simultaneously. A case study involving several price scenarios illustrates the benefits from using the model-based optimization method for deciding crude procurement, the grade of the LBO to be produced, and the conversion rate in the lube process.
Long‐term design and planning of shale gas field development is challenging due to the complex development operations and a wide range of candidate locations. In this work, we focus on the ...multi‐period shale gas field development problem, where the shale gas field has multiple formations and each well can be developed from one of several alternative pads. The decisions in this problem involve the design of the shale gas network and the planning of development operations. A mixed‐integer linear programming (MILP) model is proposed to address this problem. Since the proposed model is a large‐scale MILP, we propose a solution pool‐based bilevel decomposition algorithm to solve it. Results on realistic instances demonstrate the value of the proposed model and the effectiveness of the proposed algorithm.
In shale gas field development, the major endogenous uncertainty comes from the production profile of candidate wells and its realization is dependent on the development decision. In this work, we ...apply multistage stochastic programming to address the shale gas field development planning problem under production profile uncertainty. Business realities such as budget limit and uncertainty resolution delay are also considered in the proposed model. To solve the multistage stochastic model, a Lagrangean decomposition method and a heuristic method are proposed. Computational results demonstrate the efficiency of the proposed methods on examples that are otherwise intractable. The optimal development strategy from the proposed model is analyzed under different levels of uncertainties. Different cases are further tested to figure out the impact of budget and resolution delay on development decisions.
Summary
Evaluation information generated by various users is processed using various requirements and data to make recommendations for solving the problems, and it analyzes satisfaction with the ...results. Despite people normally utilizes the processed information for decision making, not all information, however, brings positive outcomes to users. There are some users who perceived it negatively. In order to minimize the occurrence of such negative effects, the analysis of various user requirements is essential as well as diversifying user inputs for each requirement. Consequently, the results from individual inputs must be predicted. In the past, since the system relies on a single‐expert system, it is necessary to accept and process various limitations of recommendation and multiple requirements. Therefore, the results of the recommendation also have various problems. In order to solve this problem, this study applied an analytic hierarchy process to multiadvisor configuration. In the proposed system, one or multiple advisors are defined, and after analyzing the predefined requirements, the system accepts only the requirements that can be processed and calculates the individual recommendation results. A recommendation system was going to be studied by learning all situation.
PDF
