Farnaz Kaviari

Cold rolling is widely recognized as a key industrial process for enhancing the mechanical properties of materials, particularly hardness, through strain hardening. Despite its importance, accurately predicting the final hardness remains a challenge due to the inherently nonlinear nature of the deformation. While several studies have employed artificial neural networks to predict mechanical properties, architectural parameters still need to be investigated to understand their effects on network behavior and model performance, ultimately supporting the design of more effective architectures. This study investigates hyperparameter tuning in artificial neural networks trained using Resilient Backpropagation by evaluating the impact of varying number of hidden layers and neurons on the prediction accuracy of hardness in 70-30 brass specimens subjected to cold rolling. A dataset of 1000 input–output pairs, containing dimensional and hardness measurements from multiple rolling passes, was used to train and evaluate 819 artificial neural network architectures, each with a different configuration of 1 to 3 hidden layers and 4 to 12 neurons per layer. Each configuration was tested over 50 runs to reduce the influence of randomness and enhance result consistency. Enhancing the network depth from one to two hidden layers improved predictive performance. Architectures with two hidden layers achieved better performance metrics, faster convergence, and lower variation than single-layer networks. Introducing a third hidden layer did not yield meaningful improvements over two-hidden-layer architectures in terms of performance metrics. While the top three-layer model converged in fewer epochs, it required more computational time due to increased model complexity and weight elements.

The challenges facing emergency managers and transportation planners in evacuating homeless individuals are exacerbated by the increasing threats from climate change and continued growth in homeless populations. This study examines homeless evacuation alternatives in Waikiki, O‘ahu, a dense urban resort destination exposed to coastal hazards. In addition to the problems of identifying homeless individuals and notifying them of impending threats and risks, there are challenges in transporting individuals to safe zones outside of harm’s way. This study evaluated the effectiveness of public and private transportation alternatives for evacuating homeless individuals. Decision trees were used to estimate the evacuation response and fatality rates during tsunamis at 3 p.m. and 3 a.m. and hurricane events. The study investigated evacuation alternatives: 1) do nothing, 2) bus evacuation, and 3) community-assisted evacuation. The research demonstrated that combining public and private transportation resources could significantly improve the survival rates of homeless individuals during evacuation. With combined public and private transportation assets, homeless survival rates were estimated to increase by 10.33% for tsunami and 39.76% for hurricane scenarios. Investigation of new collaborative strategies and improved coordination in emergency evacuation planning will save even more lives and enhance social equity during disasters.