Search

Purpose – Present a method to impute missing data from a chaotic time series, in this case lightning prediction data, and then use that completed dataset to create lightning prediction forecasts. Design/methodology/approach – Using the technique of spatiotemporal kriging to estimate data that is autocorrelated but in space and time. Using the estimated data in an imputation methodology completes a dataset used in lightning prediction. Findings – The techniques provided prove robust to the chaotic nature of the data, and the resulting time series displays evidence of smoothing while also preserving the signal of interest for lightning prediction. Research limitations/implications – The research is limited to the data collected in support of weather prediction work through the 45th Weather Squadron of the United States Air Force. Practical implications – These methods are important due to the increasing reliance on sensor systems. These systems often provide incomplete and chaotic data, which must be used despite collection limitations. This work establishes a viable data imputation methodology. Social implications – Improved lightning prediction, as with any improved prediction methods for natural weather events, can save lives and resources due to timely, cautious behaviors as a result of the predictions. Originality/value – Based on the authors’ knowledge, this is a novel application of these imputation methods and the forecasting methods.

Purpose – This paper aims to examine whether changing the clustering of countries within a United States Combatant Command (COCOM) area of responsibility promotes improved forecasting of conflict. Design/methodology/approach – In this paper statistical learning methods are used to create new country clusters that are then used in a comparative analysis of model-based conflict prediction. Findings – In this study a reorganization of the countries assigned to specific areas of responsibility are shown to provide improvements in the ability of models to predict conflict. Research limitations/implications – The study is based on actual historical data and is purely data driven. Practical implications – The study demonstrates the utility of the analytical methodology but carries not implementation recommendations. Originality/value – This is the first study to use the statistical methods employed to not only investigate the re-clustering of countries but more importantly the impact of that change on analytical predictions.

Purpose – Large/stochastic spatiotemporal demand data sets can prove intractable for location optimization problems, motivating the need for aggregation. However, demand aggregation induces errors. Significant theoretical research has been performed related to the modifiable areal unit problem and the zone definition problem. Minimal research has been accomplished related to the specific issues inherent to spatiotemporal demand data, such as search and rescue (SAR) data. This study provides a quantitative comparison of various aggregation methodologies and their relation to distance and volume based aggregation errors. Design/methodology/approach – This paper introduces and applies a framework for comparing both deterministic and stochastic aggregation methods using distance- and volume-based aggregation error metrics. This paper additionally applies weighted versions of these metrics to account for the reality that demand events are nonhomogeneous. These metrics are applied to a large, highly variable, spatiotemporal demand data set of SAR events in the Pacific Ocean. Comparisons using these metrics are conducted between six quadrat aggregations of varying scales and two zonal distribution models using hierarchical clustering. Findings – As quadrat fidelity increases the distance-based aggregation error decreases, while the two deliberate zonal approaches further reduce this error while using fewer zones. However, the higher fidelity aggregations detrimentally affect volume error. Additionally, by splitting the SAR data set into training and test sets this paper shows the stochastic zonal distribution aggregation method is effective at simulating actual future demands. Originality/value – This study indicates no singular best aggregation method exists, by quantifying trade-offs in aggregation-induced errors practitioners can utilize the method that minimizes errors most relevant to their study. Study also quantifies the ability of a stochastic zonal distribution method to effectively simulate future demand data.

Purpose – This paper aims to define the class of fragment constructive heuristics used to compute feasible solutions for the traveling salesman problem (TSP) into edge-greedy and vertex-greedy subclasses. As these subclasses of heuristics can create subtours, two known methodologies for subtour elimination on symmetric instances are reviewed and are expanded to cover asymmetric problem instances. This paper introduces a third novel subtour elimination methodology, the greedy tracker (GT), and compares it to both known methodologies. Design/methodology/approach – Computational results for all three subtour elimination methodologies are generated across 17 symmetric instances ranging in size from 29 vertices to 5,934 vertices, as well as 9 asymmetric instances ranging in size from 17 to 443 vertices. Findings – The results demonstrate the GT is the fastest method for preventing subtours for instances below 400 vertices. Additionally, a distinction between fragment constructive heuristics and the subtour elimination methodology used to ensure the feasibility of resulting solutions enables the introduction of a new vertex-greedy fragment heuristic called ordered greedy. Originality/value – This research has two main contributions: first, it introduces a novel subtour elimination methodology. Second, the research introduces the concept of ordered lists which remaps the TSP into a new space with promising initial computational results.

Purpose – The purpose of this paper is to demonstrate an improved method for forecasting the US Army recruiting. Design/methodology/approach – Time series methods, regression modeling, principle components and marketing research are included in this paper. Findings – This paper found the unique ability of multiple statistical methods applied to a forecasting context to consider the effects of inputs that are controlled to some degree by a decision maker. Research limitations/implications – This work will successfully inform the US Army recruiting leadership on how this improved methodology will improve their recruitment process. Practical implications – Improved US Army analytical technique for forecasting recruiting goals.. Originality/value – This work culls data from open sources, using a zip-code-based classification method to develop more comprehensive forecasting methods with which US Army recruiting leaders can better establish recruiting goals.

Although there are a variety of heuristics developed and applied to the variants of the binary knapsack problem, the testing of these heuristics are based on poorly defined test problems. This paper reviews the various types of knapsack problems, considers how test problems have been generated and depicts via empirical results the implications of using poorly formed test problems for empirical testing.