Micro-Clustering and Rank-Learning Profiling of a Small Water-Quality Multi-Index Dataset to Improve a Recycling Process

Abstract

The efficiency improvement of wastewater recycling has been prioritized by ‘Goal 6’ of the United Nations Sustainable Development initiative. A methodology is developed to synchronously profile multiple water-quality indices of a wastewater electrodialysis (ED) process. The non-linear multifactorial screener is exclusively synthesized by assembling proper R-based statistical freeware routines. In sync with current trends, the new methodology promotes convenient, open and rapid implementation. The new proposal unites the ‘small-and-fast’ data-sampling features of the fractional multifactorial designs to the downsizing, by microclustering, of the multiple water quality indices—using optimized silhouette-based classification. The non-linear multifactorial profiling process is catalyzed by the ‘ordinalization’ of the regular nominal nature of the resulting optimum clusters. A bump chart screening virtually eliminates weak performances. A follow-up application of the ordinal regression succeeds in assigning statistical significance to the resultant factorial potency. The rank-learning aptitude of the new profiler is tested and confirmed on recently published wastewater ED-datasets. The small ED-datasets attest to the usefulness to convert limited data in real world applications, wherever there is a necessity to improve the quality status of water for agricultural irrigation in arid areas. The predictions have been compared with other techniques and found to be agreeable.

Databionic Swarm Intelligence to Screen Wastewater Recycling Quality with Factorial and Hyper-Parameter Non-Linear Orthogonal Mini-Datasets

“…Consequently, the overall factorial screening prediction suggests the predominance of factor A (dilute flow), as it is now clearly construed from Figures 7 and 9. The final outcome agrees with: (1) a non-parametric statistical method prediction [59], (2) a combination of semi-unsupervised (silhouette method)/statistical method with confirmation data [60] and (3) a combination of unsupervised (affinity propagation clustering)/information-entropic methods with confirmation data [61]. OR PEER…”

“…(2) SAR: the sodium adsorption ratio; and (3) SSP: the soluble sodium percentage (%). There are previous comments on the investigated water quality indices and their pivotal value in the cultivation management of productive crops [60]. The dataset is described in ref.…”

“…The unreplicated-saturated non-linear multi-response ED dataset of Abu-Shady [16] was analyzed using descriptive and graphical Taguchi methods; a 'one-response-at-a-time' analysis is a rudimentary data reduction phase in aquametrics. There were further attempts to add significance to the original experimental outcomes using: (1) a non-parametric multifactorial technique [59], (2) a combination method of a micro-clustered dimension-reduction with rank learning [60] and (3) a combination method of unsupervised clustering with entropic methods [61]. The proposed work implements a recently published algorithmic classification method, the bionic swarm intelligence (DBSc) method [62], to structured multidimensional mini datasets.…”

IoT-Based Automatic Water Quality Monitoring System with Optimized Neural Network

“…The exploratory data analysis is conducted for the selected dataset [16] to find the correlation between the variables and the water quality. The heat map of various input parameters is shown in Fig.…”

Datacentric Similarity Matching of Emergent Stigmergic Clustering to Fractional Factorial Vectoring: A Case for Leaner-and-Greener Wastewater Recycling

“…The most striking feature is the negation of the necessity for a global objective function to guide the solver procedure. This lessens the possibility of subjectively selecting a route to narrow down the screening/optimization path; it makes the solution more abstract and it definitely differentiates it from other smart aquametric approaches [78][79][80].…”