This research looks at different ways computers can automatically spot skin cancer from images of skin problems. They tested two main approaches. The first one pulls out important details from images using basic tools and then feeds those details into various machine learning programs to make a diagnosis. The second approach uses more advanced deep learning methods like convolutional neural networks that can both find the important image details and make the diagnosis all in one go. The researchers tried out several traditional machine learning methods including Logistic Regression, k-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, and Support Vector Machine. They also tested four different CNN models: VGG16, ResNet60, InceptionV3, and Inception-ResNetV2. For the first approach, they used four different ways to pull out image features and combined them together to get the best possible feature set, which should lead to better accuracy in spotting cancer. To test how well these methods work, they used a collection of skin lesion images from the ISIC database that includes both harmless and cancerous skin conditions. They measured how effective each algorithm was using standard performance metrics and also kept track of how long each one took to train, giving them insight into both accuracy and computational demands.

This paper is a comparative between classical, hybrid and heuristic shortest path algorithms. Shortest path algorithms are necessary in graph theory and has different applications in operations research, artificial intelligence, networking, and transportation. In dynamic or huge graphs, the deterministic correctness and limitations of classical algorithms such as Dijkstra's and Bellman-Ford have been investigated. The current research examined the flexibility and scalability of heuristic techniques like Ant Colony Optimization, A*, and Genetic Algorithms. Furthermore, examined the potential to improve and enhance the accuracy of hybrid algorithms that include characteristics from both categories has been studied. This work employs important evaluation standards, for instance, optimality, time complexity, and scalability, to inspect the theoretical underpinnings, practical applications, and performance compromises of each strategy.

Global warming is major challenge facing mankind globally due to rampant deforestation and emission of greenhouse gases. The pressure on the natural resources has been increasing proportionately with population which needs more food, shelter, textiles, energy and chemicals for day-to-day life. In recent years, research efforts have been made to explore opportunities for utilization of agricultural wastes for enhancement of the circular economy. For instance, considering that Uganda is the largest producer of banana in Africa and the second largest in the world, and that 60% of banana plant is waste, this poses threats and economic opportunities in equal measure in the region. Therefore, efforts to sustainably utilize banana waste are of great importance to reduce their room for decomposition hence greenhouse gas emissions. This review takes stock of the economic opportunities for people in banana growing regions beyond the dining table by exploring sustainable uses of banana wastes as raw materials for fertilizers, textile and bio-fuel. It is here concluded that for realistic conservation of environment, more research is needed on sustainable use of banana waste for briquette production in east Africa which uses cassava starch as binder. Both banana and cassava are widely planted in east Africa but more in Uganda. Use of banana waste and cassava starch in briquette production will ensure reduced global warming, reduced cost of living, creation of new jobs and increased income from the crops.

Accurate estimation of support moments in continuous beams is essential for ensuring structural safety, serviceability, and material efficiency in modern reinforced concrete design. Despite advancements in computational modeling, inconsistencies persist between classical analytical predictions and finite element (FE) simulations, particularly at internal supports where stress concentrations and boundary idealizations strongly influence results. This study addresses this gap by conducting a comparative analysis of support moment variability in double-span continuous beams under symmetric loading, using classical analytical methods the Slope Deflection Method, Moment Distribution Method, and Clapeyron’s Three-Moment Theorem alongside finite element modeling (FEM) in STAADPro. The beams were modeled as linearly elastic, isotropic elements with uniform stiffness, subjected to both point and uniformly distributed loads. Analytical and numerical results were compared using percentage deviation analysis to evaluate consistency and accuracy. The results revealed a strong correlation between analytical and finite element outcomes, with an average deviation of approximately 9.7%, confirming that both approaches yield reliable support moment predictions within acceptable engineering tolerances. Minor discrepancies were attributed to mesh discretization, stiffness distribution, and boundary flexibility inherent in FEM modeling. The study found that analytical methods provided transparent and computationally efficient solutions, while finite element analysis offered refined accuracy and visualization of structural responses. These findings highlight the complementary roles of analytical and numerical approaches in structural analysis, reinforcing the continued relevance of classical theory for design verification and educational application. The research provides a harmonized framework for integrating analytical and computational techniques in beam design, offering practical guidance for engineers and educators while promoting accuracy, efficiency, and compliance with performance-based structural design standards.