Browsing by Author "Chen, Sheng-, I"

Now showing 1 - 3 of 3

A multi-stage stochastic programming model of lot-sizing and scheduling problems with machine eligibilities and sequence-dependent setups
(1970-01-01)
Chen, Sheng-, I
;
Su, Delvinia
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
We focus on the lot-sizing and scheduling problem with the additional considerations of machine eligibility, sequence-dependent setups, and uncertain demands. Multi-stage stochastic programming is proposed. We analyze the problem structure and suggest ways for modeling and solving large-scale stochastic integer programs. The analysis compares deterministic and stochastic model solutions to assess demand variance effects under the circumstances of increasing, fluctuating, and decreasing demands. The result shows that the expected cost performance of the stochastic programming model outperforms that of the deterministic model, in particular, when the demand is highly uncertain in the circumstance of an upward market trend. Our study can apply to the wafer fab manufacturing and other industries that heavily restricted by machine eligibility and demand uncertainties.
Evaluating the impact of soy compounds on breast cancer using the data mining approach
(2020-05-01)
Chen, Sheng-, I
;
Tseng, Hsiao-Ting
;
Hsieh, Chia-Chien
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Accumulating evidence has shown that soy intake is associated with the promotion of health and prevention of cancers. However, the relationship between the intake of soy compounds and the risk of breast cancer is still debatable. In this study, we use mathematical models for assessing the impact of soy phytoestrogens and protein/peptide intervention on breast cancer development using the datasets acquired from a large number of published studies. We used data mining models, including the decision tree classification and association rule methods, to analyze 478 data collected from 201 research papers. The results indicated that the intervention of soy proteins and peptides, especially lunasin (LUN) and bowman-birk protease inhibitor (BBI), has a positive impact on different types of breast cancer, while the effects of soy phytoestrogens are inconsistent in breast cancer development. Among soy phytoestrogens, daidzein (DAI) exhibited the highest negative impact on breast cancer, followed by coumestrol (COU), soysapogenol (SAP), genistein (GEN), and equol (EQ). With regard to the type of cancer, phytoestrogens should be carefully considered in estrogen receptor (ER)+ or progesterone receptor (PR)+ breast cancer. In the case of ER-, PR- or triple negative type, both soy categories can be used as auxiliary interventions. In summary, this is the first study to use data mining to explore the relationship between the intake of soy phytoestrogens or proteins/peptides and breast cancer development. Our findings indicate that soy intervention might reduce breast cancer development. However, the specific soy compound and cancer type should be considered before allocating a precise nutrient intervention.
Single machine scheduling with sequence-dependent setup times and delayed precedence constraints
(2020-06-01)
Kuo, Yiyo
;
Chen, Sheng-, I
;
Yeh, Yen-Hung
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This research deals with the single machine scheduling problem of minimizing the makespan with sequence dependent setup times and delayed precedence constraints. A makespan calculation model is first proposed. When given a feasible job sequence, the proposed model can calculate the makespan. Then a variable neighbourhood search (VNS) with four phases is proposed for optimizing the job sequence. The proposed VNS adopts five operations to search for new solutions, and modifies all solutions to satisfy precedence constraints. The proposed VNS will accept a worse solution over a better solution with a certain probability, in order to escape from a local optimum. The experimental results show that the proposed VNS provides the best results with less than 10 s of computation time. Therefore it is efficient and effective in solving the single machine scheduling problems.