The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network’s determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map. To fill this research gap, we first propose a VGG-16-architecture-based deep learning approach in combination with image enhancement, segmentation-based region of interest (ROI) cropping, and data augmentation steps to enhance classification accuracy. Later, a multi-layer Gradient CAM (ML-Grad-CAM) algorithm is integrated to generate a class-specific saliency map for improved visualization in CXR images. We also define and calculate a Severity Assessment Index (SAI) from the saliency map to quantitatively measure infection severity. The trained model achieved an accuracy score of 96.44% for the three-class CXR classification task, i.e., COVID-19, pneumonia, and normal (healthy patients), outperforming many existing techniques in the literature. The saliency maps generated from the proposed ML-GRAD-CAM algorithm are compared with the original Gran-CAM algorithm.

Two important factors that affect outsourcing decisions are the production cost and the potential loss of customer goodwill due to late orders. This article deals with the problem of finding outsourcing strategies or solutions that consider trade-offs between outsourcing cost and average tardiness, an important measure of lost customer goodwill. Assumptions include that outsource costs are a function of machine use and that the planning organization owns no production equipment; instead, the production function is completely outsourced. Furthermore, the planning organization has flexibility in terms of the quantity of parallel production resources to outsource and it controls the assignment of jobs to these parallel production resources. The article presents lower bounds for the problem, which are used for comparisons. Several approaches to generate trade-off solutions are proposed and compared under a variety of experimental factors.

Laser Powder Bed Fusion (LPBF) is a widely used additive manufacturing technique for powder-based polymers and metallic materials. Thermoplastics like Polyamide 12 and Polyamide 6 are commonly used in LPBF; thermosetting polymers are gaining attention due to their superior stability. Epoxies are a popular thermoset, but some exhibit low physical properties and brittleness, leading to reduced toughness. The work presented in this paper explores the effect of using short carbon fibers (CF) as additives to epoxy-based thermosetting material on physical and thermomechanical properties. A total of six epoxy thermoset/CF composite powder blends were prepared by varying reinforcing materials weight percentages (0 wt%, 0.3 wt%, 0.6 wt%, 1 wt%, 5 wt%, and 10 wt%). Tensile, four-point bending, and dynamic mechanical analysis (DMA) test samples were printed using the LPBF technique. Significant improvements in the physical and thermomechanical properties were obtained in the thermoset composites with 5 wt% of CF due to good adhesion between reinforcing materials and the matrix and a low level of porosity. Fracture surface analysis was performed via scanning electron microscopy (SEM), which provided insight into the influence of CF on the properties of thermosetting composites. The findings of this research demonstrate the feasibility of improving the inferior physical and thermomechanical properties of 3D-printed CF-reinforced epoxy. With a certain amount of CF reinforcement, Young’s modulus and fracture modulus can be increased by around 52% and 259%, respectively.

Journal of the Operational Research Society (JORS) is the world's longest established OR journal and an official journal of The OR Society. It is the aim of the Journal to present papers which are relevant to practitioners, researchers, teachers, students and consumers of operational research, and which cover the theory, practice, history or methodology of OR.