Indicating if water is safe for human consumption using an enhanced machine learning approach

Statistics, Optimization and Information Computing

article

Mourad Nachaoui¹  Soufiane Lyaqini²  Marouane Chaouch¹ 

[1] Faculté de Sciences et Technique, Université Sultan Moulay Slimane;Hassan First University of Settat, Ecole Nationale des Sciences Appliquees, LAMSAD Laboratory

关键词: Supervised learning;    Smooth approximation;    Hing loss;    Tikhonov regularization;    Taylor polynomials;    Conjugate gradient;    Water quality.;   

DOI  :  10.19139/soic-2310-5070-1703

来源: Istituto Superiore di Sanita

【 摘 要 】

Predicting water quality accurately is critically important in real-life water resource management. This work proposes an approach based on supervised machine learning to predict water quality. Motivated, by the success of the non-smooth loss function for supervised learning problems [22], we reformulate the learning problem as a regularized optimization problem whose fidelity term is the hinge loss function and the hypothesis space is a polynomial approximation. To deal with the non-differentiability of the loss function, a special smoothing function is proposed. Then, the obtained optimization problem is solved by an improved conjugate gradient algorithm. Finally,some experiments results are presented.

【 授权许可】

Unknown