Identification of Genuine from Fake Banknotes Using an Enhanced Machine Learning Approach

Lyaqini, Soufiane; Nachaoui, Mourad

doi:10.1007/978-3-030-83442-5_5

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This control surface is (12). The "product" operation is used for "AND" for WABL defuzzification close to the ones obtained using the WAF and QM when the product is used for "AND" and rules as in the Figures (13) and (14). The plot obtained using the WABL method with products, however, is better than those obtained using the other ones.…”

Section: Generalization Of the Wabl Methodssupporting

confidence: 63%

See 1 more Smart Citation

An improved hybrid defuzzification method for fuzzy controllers

Nachaoui

Shikhlinskaya

et al. 2023

Stat., optim. inf. comput.

View full text Add to dashboard Cite

This paper deals with fuzzy logic controllers. Our interest is in studying different techniques of defuzzification methods. In particular, we propose a generalization of the WABL method to the multiple output system controller. We give a numerical realization, and we show the advantages of this method compared to other defuzzification methods (MOM, COG, WAF,\ldots) through an application for intelligent control of air conditioners.

show abstract

Section: Generalization Of the Wabl Methodssupporting

confidence: 63%

“…Artificial Intelligence is one of the most investigated scientific fields [5,12,13,14]. It consists of enabling the computer to think and decide in some tasks that require intelligence.…”

Section: Introductionmentioning

confidence: 99%

An improved hybrid defuzzification method for fuzzy controllers

Nachaoui

Shikhlinskaya

et al. 2023

Stat., optim. inf. comput.

View full text Add to dashboard Cite

show abstract

“…In our case we choose to evaluate the proposed method through real-life data from from Kaggle called water potability [33]. To evaluate the efficiency of the proposed algorithm, we compared its accuracy with the K-Nearest Neighbors (KNN) [37,38], Na?ve Bayes (NB) [34,35] and Support Vector Machine (SVM) [31,32] algorithms . The goal is to show that the proposed approach is faithfully to predict the considered class and we investigate on the importance of the features to find out which features contribute to most towards achieving the result.…”

Section: Resultsmentioning

confidence: 99%

“…According to Lemma 1 in [32], we have that as γ tends to +∞, the smoothed hinge loss γ approaches the hinge loss . Then, γ is used here to replace the the hinge loss in the problem (7).…”

Section: The Reformulated Supervised Learning Problemmentioning

confidence: 99%

“…However, the optimization problem ( 7) is nonsmooth which does not allow the use of algorithms based on the gradient. To circumvent this problem the hinge loss function can be accurately approximated by a smooth function which is twice differentiable and convex [32]. For all s ∈ R, the max function is approximated by a smooth function,…”

Section: The Reformulated Supervised Learning Problemmentioning

confidence: 99%

See 1 more Smart Citation

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

Nachaoui

Lyaqini

Chaouch

2023

Stat., optim. inf. comput.

View full text Add to dashboard Cite

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.

show abstract