Northumbria University

About: Northumbria University is a education organization based out in Newcastle upon Tyne, United Kingdom. It is known for research contribution in the topics: Context (language use) & Population. The organization has 5624 authors who have published 17423 publications receiving 381949 citations. The organization is also known as: University of Northumbria at Newcastle.

Feature selection using firefly optimization for classification and regression models

Abstract: In this research, we propose a variant of the Firefly Algorithm (FA) for discriminative feature selection in classification and regression models for supporting decision making processes using data-based learning methods. The FA variant employs Simulated Annealing (SA)-enhanced local and global promising solutions, chaotic-accelerated attractiveness parameters and diversion mechanisms of weak solutions to escape from the local optimum trap and mitigate the premature convergence problem in the original FA algorithm. A total of 29 classification and 11 regression benchmark data sets have been used to evaluate the efficiency of the proposed FA model. It shows statistically significant improvements over other state-of-the-art FA variants and classical search methods for diverse feature selection problems. In short, the proposed FA variant offers an effective method to identify optimal feature subsets in classification and regression models for supporting data-based decision making processes.

Consistency of perceptual and metabolic responses to a laboratory-based simulated 4,000-m cycling time trial

Abstract: Although pacing-related research is widely reported, no studies have described the consistency of pacing strategies or their associated energetic contributions. This study aimed to investigate the consistency of pacing and energetic outlay by establishing the typical within and between trial variations during simulated 4,000 m time trials. Fifteen well-trained male cyclists performed three, 4,000 m time trials with 3-7 days separating each trial. Power output, cadence, heart rate, respiratory exchange and iEMG of the vastus lateralis were recorded continuously throughout each trial. To examine within-trial variability, the data were assigned to 10% bins. Rating of perceived exertion and affective response were recorded every 400 m and a capillary blood sample was collected and assayed for blood lactate concentration every 800 m. Mean typical error across trials 1-3 for all variables was low (range 2.1-6.3%) and lower between trials 2-3 for all variables with the exception of cadence. There were no between-trial differences in pacing strategy; however, typical error for each 10% bin was lower between trials 2-3 than trials 1-2. Anaerobic contribution to power was greatest during the first and last 10% of each trial (p > 0.05). In conclusion, well-trained cyclists demonstrated a high degree of consistency in terms of the pacing strategy they adopted which coincided with similar levels of energy distribution and perceived exertion. A laboratory simulated 4-km cycling trial is a reliable test that may be used to monitor performance and pacing strategy.