Search

Colon cancer is the third most common cancer type worldwide in 2020, almost two million cases were diagnosed. As a result, providing new, highly accurate techniques in detecting colon cancer leads to early and successful treatment of this disease. This paper aims to propose a heterogenic stacking deep learning model to predict colon cancer. Stacking deep learning is integrated with pretrained convolutional neural network (CNN) models with a metalearner to enhance colon cancer prediction performance. The proposed model is compared with VGG16, InceptionV3, Resnet50, and DenseNet121 using different evaluation metrics. Furthermore, the proposed models are evaluated using the LC25000 and WCE binary and muticlassified colon cancer image datasets. The results show that the stacking models recorded the highest performance for the two datasets. For the LC25000 dataset, the stacked model recorded the highest performance accuracy, recall, precision, and F1 score (100). For the WCE colon image dataset, the stacked model recorded the highest performance accuracy, recall, precision, and F1 score (98). Stacking-SVM achieved the highest performed compared to existing models (VGG16, InceptionV3, Resnet50, and DenseNet121) because it combines the output of multiple single models and trains and evaluates a metalearner using the output to produce better predictive results than any single model. Black-box deep learning models are represented using explainable AI (XAI).

Robust design problems in flow networks involve determining the optimal capacity assignments that enable the network to operate effectively even in the case of events’ occurrence such as arcs or nodes’ failures. Multi-source multi-sink flow networks (MMSFNs) are frequent in many real-life systems such as computer and telecommunication, logistics and supply-chain, and urban traffic. Although numerous studies on the design of MMSFNs have been conducted, the robust design problem for multi-source multi-sink stochastic-flow networks (MMSFNs) remains unexplored. To contribute to this field, this study addresses the robust design problem for MMSFNs using an approach of two steps. First, the problem is mathematically formulated as an optimization problem and second, a sub-optimal solution is proposed based on a genetic algorithm (GA) involving two components. The first component, an outer genetic algorithm, is employed to search the optimal capacity assigned to the network components with minimum sum. The second component, an inner genetic algorithm, is used to find the optimal flow vectors that maximize the system’s reliability. Through extensive experimentation on three different networks with different topologies, the proposed solution has been found to be efficient.