The interactive decision support system for weaving process dispatching
(直覺互動式梭織製程派工決策支援系統)
We developed an interactive decision support system (DSS) for weaving process dispatching. The DSS helps users (decision makers) dispatching beams (jobs) to looms (machines) based on their decision preferences and practical considerations. The graphical user interface (GUI) visualizes the decision process and results; it allows users to manually dispatch beams to looms while the feedbacks (predicted multicriteria performance) are displayed on the dashboard immediately. The DSS also has a dispatching optimizer embedded, which suggests an optimal dispatching based on the mathematical programming techniques. Users can adopt the suggestion or modify it to fit their needs.
High-performance DEA computation
FrontierEfficiencyAnalysis.jl is a package for Frontier Efficiency Analysis (aka Data Envelopment Analysis, DEA) computation. It is embedded in the Julia programming language, and is an extension to the JuMP modeling language. It is particularly designed to enhance large-scale DEA computation and to solve DEA problems by size-limited solvers (e.g. 300 variables). While enjoying the attractive features of JuMP, such as easy-to-learn and flexibility, FrontierEfficiencyAnalysis.jl provides better computational performance on the top of open-source or commercial solvers. The theoretical development can be found in (Chen and Lai, 2017) and (Chen and Chung, 2017).
SearchRef.jl is a Julia package for computing efficiency based on the input-oriented VRS DEA model. It is based on a new computation algorithm (Chen, 2017) to determine DEA efficiencies by solving small-size LPs instead of a full-size LP. The concept is based on searching the corresponding references, which is a subset of the efficient DMUs with numbers no greater than the dimension (number of inputs and outputs). The results of empirical case studies show that the proposed algorithm computes 3 times faster than the current state of the art for large-scale, high-dimension, and high-density (percentage of efficient DMUs) cases. It is flexible enough to compute the efficiencies of a subset of the full data set without setup costs, and it can also serve as a sub-procedure for other algorithms.
Codes for DEA reaserach
You can find some Julia codes for DEA computation in my GitHub site. They use the Julia package, JuMP, for mathematical modeling, and thus are easy to modify to new applications.
example.jl is a simple JuMP code for the input-oriented CRS (CCR) model.
basicDEAmodel.jl is the code for computing DEA models based on input- or output- orientation and different returns to scale.
outlierDetection.jl implements the model to detect efficient and inefficient outliers (Chen and Johnson, 2010).