A New Function for Ensemble Pruning

Zouggar, Souad Taleb; Adla, Abdelkader

doi:10.1007/978-3-319-90315-6_15

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Voting selects the class mostly predicted by induvial models. Most importantly, as presented in [19], the WVE whose output y(x) can be expressed through equation (1), is an improved variant of simple voting which was introduced with an understanding that different individual models to form an ensemble cannot in most practical cases have same influence within that formation, in turn specifying a weight coefficient often between 0 and 1 for each member which can be same or different depending on optimality of the ensemble thereof and whose total weight summation should be equal to one as in equation ( 2) can provide better predictive performance, unlike in simple voting which barely assume models are equal [20,21,22,23].…”

Section: Weighted Voting Ensemble (Wve)mentioning

confidence: 99%

Brute Exhaustive Optimization of Intelligent Small Weighted Voting Ensembles in 1EXP(-)Z+ Initial-Term based Arithmetic Sequence’s Multi Precision Search Spaces

Malamsha,

Ally Dida,

Moebbs

2023

JMI

View full text Add to dashboard Cite

Other than the individual machine learning models' capabilities, the weighted voting ensemble (WVE) technique relies on appropriate weight assignment in order to significantly realize prediction performance improvement. Often evolutionary global or grid local search heuristics are being applied for such a challenging optimization task. However, these techniques do not guarantee optimal solution finding. In turn, the surprising outstanding successes of brute exhaustive search procedure in producing similar results shed light on its significance and the need to exploit its possible weights solutions search space(s) with corresponding sizes as a key determinant factor for implementing a successful brute search procedure for finding optimal WVE solution with a trade-off the computational efficiency. This paper formulates an asymptotically WVE weights domain constraints optimal 1EX(-)Z + initial term-based arithmetic sequences initialization function, and then a computational multi-precision search space-based generation algorithm is developed to find optimal WVE solution as part of the brute exhaustive search procedure. It took 45 minutes for a proposed algorithm to generate 133,192 combinations and find the optimal solution in weights space of precision 0.01.

show abstract

Section: Weighted Voting Ensemble (Wve)mentioning

confidence: 99%

Brute Exhaustive Optimization of Intelligent Small Weighted Voting Ensembles in 1EXP(-)Z+ Initial-Term based Arithmetic Sequence’s Multi Precision Search Spaces

Malamsha,

Ally Dida,

Moebbs

2023

JMI

View full text Add to dashboard Cite

show abstract

“…If this change leads to a better solution, another change will be made to this new solution. This process will continue until there is no further improvement in the solution [14].…”

Section: Hill Climbing Algorithmmentioning

confidence: 99%

An adaptive hybrid algorithm for social networks to choose groups with independent members

Hadikhani¹,

Hadikhani

2020

Evol. Intel.

View full text Add to dashboard Cite

Choosing a committee with independent members in social networks can be named as a problem in group selection and independence in the committee is considered as the main criterion of this selection. Independence is calculated based on the social distance between group members. Although there are many solutions to solve the problem of group selection in social networks, such as selection of the target set or community detection, just one solution has been proposed to choose committee members based on their independence as a measure of group performance. In this paper, a new adaptive hybrid algorithm is proposed to select the best committee members to maximize the independence of the committees. This algorithm is a combination of particle swarm optimization (PSO) algorithm with two local search algorithms. The goal of this work is to combine exploration and exploitation to improve the efficiency of the proposed algorithm and obtain the optimal solution. Additionally, to combine local search algorithms with particle swarm optimization, an effective selection mechanism is used to select a suitable local search algorithm to combine with particle swarm optimization during the search process. The results of experimental simulation are compared with the well-known and successful metaheuristic algorithms. This comparison shows that the proposed method improves the group independence by at least 21%.

show abstract

“…WVE was fundamentally introduced with this key understanding that different individual models to form an ensemble cannot in most practical cases have the same influence, thus treating them unequally and weighing their class probabilities prediction with unequal weights whereby the total sum of all models weights is equal to one (1) as represented in equation ( 2) (Brownlee, 2021;Dolzhikova et al, 2021;Escorcia-Gutierrez et al, 2022;Shahhosseini et al, 2019;Zouggar & Adla, 2018).…”

Section: Boostingmentioning

confidence: 99%

Developing a high-performance soil fertility status prediction voting ensemble using brute exhaustive optimization in automated multiprecision weights of hybrid classifiers

Josephat

View full text Add to dashboard Cite

With the advent of machine learning (ML) techniques, various algorithms have been applied in previous studies to develop models for predicting soil fertility status. However, these models are observed to use varying fertility target classes, and variations have been reported in these models' predictive performances. As a result, practical applications of these models for obtaining the most accurate predictions may become hindered. While the weighted voting ensemble (WVE) ML technique can be used to improve soil fertility status prediction by aggregating individual models prediction, guaranteeing finding of an optimal WVE assignment weights is challenging. Whereas a brute exhaustive search procedure can be applied for the mentioned task, there is a lack of exploration on the exploitation of automated classifiers' precise weights combinations as search spaces for successful optimization. This research aims to develop a high-performance soil fertility status prediction voting ensemble using brute exhaustive optimization in automated 1EXP(-)Z+ multi-precision weights of hybrid classifiers. Soil chemical properties and ML modeling algorithms for modeling soil fertility status were identified. Base hybrid ML classification models for predicting soil fertility status were evaluated using Tanzania as a case study. Finally, the base ML hybrids WVE models were optimized using brute exhaustive search procedure’s novel developed search spaces generation algorithm for guaranteed optimal solution finding. The research was designed using design science research methodology, with the application of unsupervised machine learning K-mean algorithm with a knee detection method to find the optimal number of soil fertility status target classes, and supervised learning algorithms were applied to model classifiers for those optimal classes. Three soil fertility target classes were identified by clustering technique. The model achieved on test data a predictive accuracy of 98.93%, with respective AUC of 82%, 83%, and 87% for low, medium, and high soil fertility targets classes. Whereas these performances are observed higher compared to models in previous studies, 92% correct classifications were obtained on validation against external unseen laboratory-based tested soil results. Therefore, soil testing laboratories and farmers should consider using the model to smartly manage soil fertility which may lead to improved crop growth and productivity. The government could set agricultural-related policies that require the use of the model by farmers with the provision of agricultural inputs subsidies. Future work could be to develop an integrated real-time web and mobile application for providing farmers with soil fertility status information.

show abstract

A New Function for Ensemble Pruning

Cited by 6 publications

References 20 publications

Brute Exhaustive Optimization of Intelligent Small Weighted Voting Ensembles in 1EXP(-)Z+ Initial-Term based Arithmetic Sequence’s Multi Precision Search Spaces

Brute Exhaustive Optimization of Intelligent Small Weighted Voting Ensembles in 1EXP(-)Z+ Initial-Term based Arithmetic Sequence’s Multi Precision Search Spaces

An adaptive hybrid algorithm for social networks to choose groups with independent members

Developing a high-performance soil fertility status prediction voting ensemble using brute exhaustive optimization in automated multiprecision weights of hybrid classifiers

Contact Info

Product

Resources

About