No abstract

The number of Neighbours (k) and distance measure (DM) are widely modified for improved kNN performance. This work investigates the joint effect of these parameters in conjunction with dataset characteristics (DC) on kNN performance. Euclidean; Chebychev; Manhattan; Minkowski; and Filtered distances, eleven k values, and four DC, were systematically selected for the parameter tuning experiments. Each experiment had 20 iterations, 10-fold cross-validation method and thirty-three randomly selected datasets from the UCI repository. From the results, the average root mean squared error of kNN is significantly affected by the type of task (p9000, as optimal performance pattern for classification tasks. For regression problems, the experimental configuration should be7000≤SS≤9000; 4≤number of attributes ≤6, and DM = 'Filtered'. The type of task performed is the most influential kNN performance determinant, followed by DM. The variation in kNN accuracy resulting from changes in k values only occurs by chance, as it does not depict any consistent pattern, while its joint effect of k value with other parameters yielded a statistically insignificant change in mean accuracy (p>0.5). As further work, the discovered patterns would serve as the standard reference for comparative analytics of kNN performance with other classification and regression algorithms.

While the development of information systems in workplaces with the aim of achieving cost-effectiveness, efficiency and quality of service delivery remain sacrosanct, issues of effective utilization and its resultant implications on organizational performance remain critical from one context to another. Unfortunately, few studies had considered focusing on these causal relationships among information system deployments in the construction industry especially in developing countries like Nigeria. This work modelled the interactions causal relationships associated with task technology fit, system usage and performance variables using the TUSPEM model. Through convenience and stratified sampling techniques, the views of 136 senior staff including top level management staff, sectional heads and other senior staff of a construction firm in Nigeria were sought. Smart PLS structural equation modeling software was used for the analysis of the dataset. The result showed significant relationships between causal variables in the TUSPEM model such as Application utilization to performance (t-value 2.44, P< 0.02), utilization to user satisfaction (t-value 2.87, P< 0.01). TTF to performance (t-value 2.86, P< 0.06), satisfaction (t-value 4.40, P< 0.00), User attitude to utilization (t-value 5.40, P< 0.00). Computer 2self-efficacy to utilization (t-value 4.47, P< 0.00). User satisfaction to performance (t-value 2.47, P< 0.01). Critical appraisal and integration of quality feedback on information system usage and its resultant effects on the numerous information systems being deployed must not be sideline if the sustainability of information system is anything to go by. Other implications are discussed.

No abstract

No abstract