We analyze the use of ℓ1-norm and Total Variation regularization within a model of road design to obtain sensible vertical alignments. With a dataset of twenty-three roads, we present a heuristic for choosing regularization parameters, and obtain cost bounds to establish a suitable choice for...

Social media data are increasingly being studied for their potential use in addressing and mitigating public health issues. Data from text and image-based social media have been used for observational and intervention studies, and have been collected from a variety of social media platforms....

Although the practicability of using wavelet neural networks (WNNs) in nonlinear function approximation has been addressed extensively, selecting the optimal number of hidden nodes and their appropriate initial locations remains a great challenge for WNNs' initialization. The cuckoo search...

Developed countries are responsible for a great share of the historical carbon dioxide (CO2) emissions in the atmosphere. The need to reduce CO2 emissions is now widely accepted, but how this can be accomplished is still controversial and debated. Considering the growing size of the carbon...

Listeriosis is a life-threatening illness that can be spread through contaminated food. The bacteria responsible for this disease is Listeria monocytogenes. The annual incidence rate ranges from less than one to more than ten per one million persons in different parts of the world. Despite the...

Plasma arc cutting (PAC) has evolved as an efficient process to cut complex profiles on many hard-to-machine engineering materials due to its many advantages, like higher dimensional accuracy, higher productivity, and the capability to cut thick materials. Optimization of this process is...

Human resources (HR) management is vital in developing organizational performance and profit maximization. Small and medium-sized enterprises (SMEs) and emerging start-ups struggle to establish a functioning HR department, while larger organizations tend to reinvent their HR functions with...

An Autoencoder (AE) is an independent feature extractor from data samples and a deep network can be obtained by stacking several AEs. This paper presents a novel hybrid stacked Autoencoder-based Deep Kernel-based Random Vector Functional Link Network (DKRVFLN-AE) for forecasting and trend...

Disasters can be caused by humans or natural hazards, and they impact the vulnerability of communities worldwide. This study considers disasters caused by humans, including the rescue operation taken post-accidents. The objective of the research is to minimise time and cost to save people's...

This study considers the classical Lotka-Volterra model for a prey-predator system with harvesting effort and catchability coefficients for both species incorporating a new prey-refuge parameter. Trapezoidal intuitionistic fuzzy numbers are considered to describe the initial values of the prey...