An eco-friendly supply chain (SC) is greatly determined by travel economy and fuel consumption rate. This research considered these two critical factors and explored the relationship between travel economy and vehicle loads, and developed mathematical models in cold-chain logistics (MMCCL) to determine fuel consumption and carbon footprint in cold-chain logistics. Longer routes are more prone to degrade food quality and endanger environmental safety by producing more carbon contents. Considering this fact, we aimed to reduce carbon emissions while maintaining food quality. First, an empirical SC was divided into three possible routes, namely, single-route transportation (SRT), and multiple-route transportation (MRT-I and MRT-II). Later, the proposed MMCCL model was deployed on each route to determine the most carbon-efficient route and found SRT as more fuel-efficient than MRT-I and MRT-II by a margin of 64.52% and 12.78%, respectively. This resulted in the reduction of carbon footprint by cutting the fuel consumption by a significant amount while making the SC eco-friendly and safe. The results were thoroughly justified and evaluated with an appropriate case study in the context of the west southern part of Bangladesh.

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.

This study introduces a novel strategy for optimizing hybrid drone-and-truck delivery systems in remote areas by leveraging geospatial analytics. Geospatial methods are employed to identify optimal depot and drone nest locations, which serve as critical nodes for efficient delivery operations. After determining these locations, a customized Vehicle Routing Problem (VRP) model is applied to solve the routing problem. We use Network Analyst (NA) from ArcGIS Pro to solve the VRP problem and improve the solution by customizing the algorithm so that all delivery orders for a vehicle are geographically clustered within the service area. Comparative analysis between truck-only and hybrid truck-and-drone scenarios reveals significant efficiency gains, including reductions in delivery routes, on-road minutes, and total miles traveled. A case study conducted in parts of Wyoming, Idaho, Nevada, Utah, and Colorado validates these findings. The results demonstrate a 10.5% reduction in delivery routes, a 15% reduction in on-road minutes, and a 28% decrease in total miles. Further improvements were achieved through spatial clustering, optimizing delivery routes by grouping orders geographically. These findings emphasize the potential of hybrid delivery systems to improve logistics in remote areas, providing actionable insights for supply chain decision-makers, highlighting the robustness of the proposed method.

Automatic extraction of filler morphology (size, orientation, and spatial distribution) in Scanning Electron Microscopic (SEM) images is essential in many applications such as automatic quality inspection in composite manufacturing. Extraction of filler morphology greatly depends on accurate segmentation of fillers (fibers and particles), which is a challenging task due to the overlap of fibers and particles and their obscure presence in SEM images. Convolution Neural Networks (CNNs) have been shown to be very effective at object recognition in digital images. This paper proposes an automatic filler detection system in SEM images, utilizing a Mask Region-based CNN architecture. The proposed system can simultaneously classify, detect, and segment fillers in SEM images, making it suitable for morphology analysis of fillers and automatic quality inspection. We also propose a novel SEM image simulation procedure to overcome the data scarcity for training a deep CNN architecture. The proposed filler detection system is trained on the simulated images. It is shown that the trained network can detect and segment fillers with higher accuracy even in the overlapping and obscure situations. The performance and robustness of the proposed system are evaluated using both simulated and real microscopic images.