Multi-objective genetic programming for feature extraction and data visualization

Cano, Alberto; Ventura, Sebastián; Cios, Krzysztof J.

doi:10.1007/s00500-015-1907-y

Cited by 46 publications

(26 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“… Evaluate the proposed approach in other multi-hop networks, such as Mobile Ad Hoc Networks (MANETs), Delay Tolerant Networks (DTNs), and Flying Ad Hoc Networks (FANETs) [ 38 , 39 ]. Since in majority of cases the proposed approach outperforms the other algorithms in terms of Re , but with an increase of redundancy, we plan to extend the work by considering a multi-objective genetic programming approach [ 40 ]. Therefore, both reachability and redundancy can be balanced.…”

Section: Simulation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Dissimilarity Metric Based on Local Neighboring Information and Genetic Programming for Data Dissemination in Vehicular Ad Hoc Networks (VANETs)

Reina

Sharma

You

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper presents a novel dissimilarity metric based on local neighboring information and a genetic programming approach for efficient data dissemination in Vehicular Ad Hoc Networks (VANETs). The primary aim of the dissimilarity metric is to replace the Euclidean distance in probabilistic data dissemination schemes, which use the relative Euclidean distance among vehicles to determine the retransmission probability. The novel dissimilarity metric is obtained by applying a metaheuristic genetic programming approach, which provides a formula that maximizes the Pearson Correlation Coefficient between the novel dissimilarity metric and the Euclidean metric in several representative VANET scenarios. Findings show that the obtained dissimilarity metric correlates with the Euclidean distance up to 8.9% better than classical dissimilarity metrics. Moreover, the obtained dissimilarity metric is evaluated when used in well-known data dissemination schemes, such as p-persistence, polynomial and irresponsible algorithm. The obtained dissimilarity metric achieves significant improvements in terms of reachability in comparison with the classical dissimilarity metrics and the Euclidean metric-based schemes in the studied VANET urban scenarios.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

“…Since in majority of cases the proposed approach outperforms the other algorithms in terms of Re , but with an increase of redundancy, we plan to extend the work by considering a multi-objective genetic programming approach [ 40 ]. Therefore, both reachability and redundancy can be balanced.…”

Section: Simulation Resultsmentioning

confidence: 99%

Dissimilarity Metric Based on Local Neighboring Information and Genetic Programming for Data Dissemination in Vehicular Ad Hoc Networks (VANETs)

Reina

Sharma

You

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…A recent work that focuses on evolutionary dimensionality reduction and consequent visualization is [21], where a multi-objective, grammar-based SGP approach is employed. K feature transformations are evolved in synergy to enable, at the same time, good classification accuracy, and visualization through dimensionality reduction.…”

Section: Related Workmentioning

confidence: 99%

On explaining machine learning models by evolving crucial and compact features

Virgolin

Alderliesten

Bosman

2020

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

Feature construction can substantially improve the accuracy of Machine Learning (ML) algorithms. Genetic Programming (GP) has been proven to be effective at this task by evolving non-linear combinations of input features. GP additionally has the potential to improve ML explainability since explicit expressions are evolved. Yet, in most GP works the complexity of evolved features is not explicitly bound or minimized though this is arguably key for explainability. In this article, we assess to what extent GP still performs favorably at feature construction when constructing features that are (1) Of small-enough number, to enable visualization of the behavior of the ML model; (2) Of small-enough size, to enable interpretability of the features themselves; (3) Of sufficient informative power, to retain or even improve the performance of the ML algorithm. We consider a simple feature construction scheme using three different GP algorithms, as well as random search, to evolve features for four ML algorithms, including support vector machines and random forest. Our results on 20 datasets pertaining to classification and regression problems show that constructing only two compact features can be sufficient to rival the use of the entire original feature set. We further find that a modern GP algorithm, GP-GOMEA, performs best overall. These results, combined with examples that we provide of readable constructed features and of 2D visualizations of ML behavior, lead us to positively conclude that GP-based feature construction still works well when explicitly searching for compact features, making it extremely helpful to explain ML models.

show abstract

“…MOEA/D has been shown to produce approximation fronts with better spread and convergence than previous EMO methods [26]. Multiobjective genetic programming (MOGP) approaches have seen significant success in recent years [10], [27].…”

Section: Multi-objective Optimisationmentioning

confidence: 99%

Genetic Programming for Evolving a Front of Interpretable Models for Data Visualization

Lensen¹,

Xue²,

Zhang³

2020

Preprint

View full text Add to dashboard Cite

Data visualization is a key tool in data mining for understanding big datasets. Many visualization methods have been proposed, including the well-regarded state-of-the-art method t-distributed stochastic neighbor embedding. However, the most powerful visualization methods have a significant limitation: the manner in which they create their visualization from the original features of the dataset is completely opaque. Many domains require an understanding of the data in terms of the original features; there is hence a need for powerful visualization methods which use understandable models. In this article, we propose a genetic programming (GP) approach called GP-tSNE for evolving interpretable mappings from the dataset to high-quality visualizations. A multiobjective approach is designed that produces a variety of visualizations in a single run which gives different tradeoffs between visual quality and model complexity. Testing against baseline methods on a variety of datasets shows the clear potential of GP-tSNE to allow deeper insight into data than that provided by existing visualization methods. We further highlight the benefits of a multiobjective approach through an in-depth analysis of a candidate front, which shows how multiple models can be analyzed jointly to give increased insight into the dataset.

show abstract

Multi-objective genetic programming for feature extraction and data visualization

Cited by 46 publications

References 53 publications

Dissimilarity Metric Based on Local Neighboring Information and Genetic Programming for Data Dissemination in Vehicular Ad Hoc Networks (VANETs)

Dissimilarity Metric Based on Local Neighboring Information and Genetic Programming for Data Dissemination in Vehicular Ad Hoc Networks (VANETs)

On explaining machine learning models by evolving crucial and compact features

Genetic Programming for Evolving a Front of Interpretable Models for Data Visualization

Contact Info

Product

Resources

About