scholarly journals Site Selection for Joint Logistics over the Shore (JLOTS) Operations Using Multi- Objective Decision Analysis

2016 ◽  
Vol 4 (2) ◽  
pp. 88-95
Author(s):  
Mike Evans ◽  
Mike Lami ◽  
Brendan Madarasz ◽  
Benjamin Smith ◽  
Chris Green
Keyword(s):  
Decision Analysis ◽  
Site Selection ◽  
Decision Support Tool ◽  
Military Operations ◽  
Support Tool ◽  
Multi Objective ◽  
Selection Protocol ◽  
Operational Criteria ◽  
A Site ◽  
Development Center

As the U.S. military faces an increasing need to deploy across a range of military operations and environments, the ability to establish and sustain logistics support remains a major challenge. The Engineer Research and Development Center is currently developing the Planning Logistics Analysis Network System (PLANS), a decision support tool, to facilitate strategic and operational logistics planning. This paper describes a site selection protocol for logistics operations occurring without a suitable port, commonly referred to as Logistics over-the Shore (LOTS) operations. The model uses multi- objective decision analysis techniques to weight different operational criteria to determine the best overall site for logistics over the shore operations. This tool will enhance the time and accuracy in determining an optimal site that meets the decision maker’s specific operational needs.

scholarly journals A Pareto Based Multi-Objective Evolutionary Algorithm Approach to Military Installation Rail Infrastructure Investment

2019 ◽  
Vol 7 (2) ◽  
pp. 64-75
Author(s):  
Eugene Lesinski ◽  
Steven Corns
Keyword(s):  
Decision Support ◽  
Evolutionary Algorithm ◽  
Lower Cost ◽  
Decision Support Tool ◽  
Decision Makers ◽  
Support Tool ◽  
Track Maintenance ◽  
Multi Objective ◽  
Military Installation ◽  
Prioritization Scheme

Decision making for military railyard infrastructure is an inherently multi-objective problem, balancing cost versus capability. In this research, a Pareto-based Multi-Objective Evolutionary Algorithm is compared to a military rail inventory and decision support tool (RAILER). The problem is formulated as a multi-objective evolutionary algorithm in which the overall railyard condition is increased while decreasing cost to repair and maintain. A prioritization scheme for track maintenance is introduced that takes into account the volume of materials transported over the track and each rail segment’s primary purpose. Available repair options include repairing current 90 gauge rail, upgrade of rail segments to 115 gauge rail, and the swapping of rail removed during the upgrade. The proposed Multi-Objective Evolutionary Algorithm approach provides several advantages to the RAILER approach. The MOEA methodology allows decision makers to incorporate additional repair options beyond the current repair or do nothing options. It was found that many of the solutions identified by the evolutionary algorithm were both lower cost and provide a higher overall condition that those generated by DoD’s rail inventory and decision support system, RAILER. Additionally, the MOEA methodology generates lower cost, higher capability solutions when reduced sets of repair options are considered. The collection of non-dominated solutions provided by this technique gives decision makers increased flexibility and the ability to evaluate whether an additional cost repair solution is worth the increase in facility rail condition.

scholarly journals Developing a Machine Learning Tool for Dynamic Cancer Treatment Strategies

2020 ◽  
Vol 34 (10) ◽  
pp. 13742-13743
Author(s):  
Jiaming Zeng
Keyword(s):  
Machine Learning ◽  
Decision Analysis ◽  
Cancer Treatment ◽  
Causal Inference ◽  
Medical Records ◽  
Treatment Strategies ◽  
Decision Support Tool ◽  
Patient Characteristics ◽  
Cancer Therapies ◽  
Support Tool

With the rising number and complexity of cancer therapies, it is increasingly difficult for clinicians to identity an optimal combination of treatments for a patient. Our research aims to provide a decision support tool to optimize and supplant cancer treatment decisions. Leveraging machine learning, causal inference, and decision analysis, we will utilize electronic medical records to develop dynamic cancer treatment strategies that advice clinicians and patients based on patient characteristics, medical history, and etc. The research hopes to bridge the understanding between causal inference and decision analysis and ultimately develops an artificial intelligence tool that improves clinical outcomes over current practices.

scholarly journals Online Decision-Support Tool “TECHoice” for the Equipment Technology Choice in Sterile Filling Processes of Biopharmaceuticals

Processes ◽  
2019 ◽  
Vol 7 (7) ◽  
pp. 448 ◽  
Author(s):  
Haruku Shirahata ◽  
Sara Badr ◽  
Yuki Shinno ◽  
Shuta Hagimori ◽  
Hirokazu Sugiyama
Keyword(s):  
Decision Support ◽  
Drug Product ◽  
Decision Support Tool ◽  
Objective Evaluation ◽  
Easy Access ◽  
Technology Choice ◽  
Support Tool ◽  
Multi Objective ◽  
Evaluation Models ◽  
Biopharmaceutical Manufacturing

In biopharmaceutical manufacturing, a new single-use technology using disposable equipment is available for reducing the work of change-over operations compared to conventional multi-use technology that use stainless steel equipment. The choice of equipment technologies has been researched and evaluation models have been developed, however, software that can extend model exposure to reach industrial users is yet to be developed. In this work, we develop and demonstrate a prototype of an online decision-support tool for the multi-objective evaluation of equipment technologies in sterile filling of biopharmaceutical manufacturing processes. Multi-objective evaluation models of equipment technologies and equipment technology alternative generation algorithms are implemented in the tool to support users in choosing their preferred technology according to their input of specific production scenarios. The use of the tool for analysis and decision-support was demonstrated using four production scenarios in drug product manufacturing. The online feature of the tool allows users easy access within academic and industrial settings to explore different production scenarios especially at early design phases. The tool allows users to investigate the certainty of the decision by providing a sensitivity analysis function. Further enrichment of the functionalities and enhancement of the user interface could be implemented in future developments.

scholarly journals Site-Scale Integrated Decision Support Tool (i-DSTss) for Stormwater Management

Water ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 2022 ◽  
Author(s):  
Shojaeizadeh ◽  
Geza ◽  
McCray ◽  
Hogue
Keyword(s):  
Decision Support ◽  
Best Management Practices ◽  
Life Cycle Cost ◽  
Management Practices ◽  
Decision Support Tool ◽  
Green Roofs ◽  
Optimization Approach ◽  
Small Catchment ◽  
Support Tool ◽  
A Site

A site-scale integrated decision support tool (i-DSTss) is developed for selection and sizing of stormwater Best Management Practices (BMPs). The tool has several component modules—hydrology, BMP selection, BMP sizing, and life-cycle cost analysis (LCCA)—integrated into a single platform. The hydrology module predicts runoff from small catchment on event and continuous basis using the Green-Ampt and Curve Number methods. The module predicted runoff from a small residential area and a parking lot with R2 value of 0.77 and 0.74, respectively. The BMP selection module recommends a BMP type appropriate for a site based on economic, technical, social and environmental criteria using a multi-criteria optimization approach. The BMP sizing module includes sizing options for green roofs, infiltration-based BMPs, and storage-based BMPs. A mass balance approach is implemented for all types of BMPs. The tool predicted outflow rates from a permeable pavement with R2 value of 0.89. A cost module is included where capital, operation and maintenance, and rehabilitation costs are estimated based on BMP size obtained from the sizing module. The i-DSTss is built on an accessible platform (Microsoft Excel VBA) and can be operated with a basic skillset. The i-DSTss is intended for designers, regulators, and municipalities for quick analysis of scenarios involving interaction among several factors.

scholarly journals A systematic decision support tool for robust hydropower site selection in poorly gauged basins

2018 ◽  
Vol 224 ◽  
pp. 309-321 ◽  
Author(s):  
Abdul Moiz ◽  
Akiyuki Kawasaki ◽  
Toshio Koike ◽  
Maheswor Shrestha
Keyword(s):  
Decision Support ◽  
Site Selection ◽  
Decision Support Tool ◽  
Support Tool ◽  
Gauged Basins
Sign in / Sign up

Export Citation Format

Share Document