SIRA: Scale illumination rotation affine invariant mask R-CNN for pedestrian detection

Applied Intelligence - In this paper, we resolve the challenging obstacle of detecting pedestrians with the ubiquity of irregularities in scale, rotation, and the illumination of the natural scene...     

Cost Savings Due to Variance Reduction in a Canning Process

We investigate a canning problem (Golhar and Pollock [2]) to study the effect of a reduction in process variance on the production cost. Exact and approximate relationships are developed for cost reduction as a function of economic parameters when the fill is a normally distributed random variable and process settings are optimized.     

An optimal ordering strategy for a third-party managed supply chain

The rapid pace of new product introduction and global sourcing of raw materials and manufacturing facilities have created a complex and fragmented supply chain. Retailers in many consumer product industries are relying on third-party supply-chain managers (SCMs) to manage the global supply chain cost-effectively with short production lead times. To meet delivery requirements, the SCM must start the production process before receiving a firm order from retailers. We assume a two-stage production process where, in stage 1, a base product is produced. In stage 2, the base product is customised. The SCM absorbs the penalties associated with over- or underestimating retailers’ demand. Hence, the SCM has to decide on (a) the optimal production quantity of the base products and (b) the number of base products to be customised without delay. We develop a profit maximisation model for this strategy using a nonlinear objective function with two decision variables and one constraint. Applying Kuhn–Tucker conditions, closed-form solutions are obtained for the two decision variables. Also, formulations are given for two additional strategies: postpone customisation of all products and produce customised products only. An example illustrates the use of our model. We also examine the impact of demand variability on the effectiveness of the three strategies. Results show that postponement may not always be the best strategy for an SCM.     

Truncated sprt for non-stationary processes: sensitivity of assumptions

There is little literature on the truncated SPRT when observations have distribution parameters that change over time. We develop a truncated SPRT when the observations come from a Normal distribution with parameters that linearly increase over time. The truncation point, specified in advance, gives error probabilities within desired limits. The method is developed for two different assumptions about the non stationary observations i) the observations are independent and ii) the differences between successive observations are independent. The sensitivity of results to these assumptions is studied.