Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

Rodrigues, Douglas; Papa, João Paulo; Adeli, Hojjat

doi:10.1111/exsy.12255

Cited by 35 publications

(24 citation statements)

References 116 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zach et al improved the Horn-Schunck model by imposing a robust L 1 data term and total variation (TV) regularization [55]. The energy function is minimized by alternating optimization strategy, see also [39,34,35,36,37]. Subsequently, Wedel et al further improved the TV − L 1 optical flow algorithm by performing a structuretexture decomposition of the images and integrating a median filter into the numerical scheme [48].…”

Section: Related Workmentioning

confidence: 99%

A multi-aperture optical flow estimation method for an artificial compound eye

Zhang

Neri

et al. 2019

ICA

View full text Add to dashboard Cite

An artificial compound eye (ACE) is a bio-inspired vision sensor which mimics a natural compound eye (typical of insects). This artificial eye is able to visualize large fields of the outside world through multi-aperture. Due to its functioning, the ACE is subject to optical flow, that is an apparent motion of the object visualized by the eye. This paper proposes a method to estimate the optical flow based on capturing multiple images (multi-aperture).In this method, based on descriptors-based initial optical flows, a unified global energy function is presented to incorporate the information of multi-aperture and simultaneously recover the optical flows of multi-aperture. The energy function imposes a compound flow fields consistency assumption along with the brightness constancy and piecewise smoothness assumptions. This formula efficiently binds the flow field in time and space, and further enables view-consistent optical flow estimation. Experimental results on real and synthetic data demonstrate that the proposed method recovers view-consistent optical flows crossed multi-aperture and performs better than other optical flow methods on the multi-aperture images.

show abstract

Section: Related Workmentioning

confidence: 99%

A multi-aperture optical flow estimation method for an artificial compound eye

Zhang

Neri

et al. 2019

ICA

View full text Add to dashboard Cite

show abstract

“…The development of modern autonomous robots poses difficult tasks associated with the interaction between the robot and the external world, see [25,64]. For example, a shape reconstruction system of 3D objects is proposed in [68] and a vision based navigation system for drones is proposed in [5].…”

Section: Introductionmentioning

confidence: 99%

A membrane parallel rapidly-exploring random tree algorithm for robotic motion planning

Pérez–Hurtado

Amor

Zhang

et al. 2020

ICA

View full text Add to dashboard Cite

In recent years, incremental sampling-based motion planning algorithms have been widely used to solve robot motion planning problems in high-dimensional configuration spaces. In particular, the Rapidly-exploring Random Tree (RRT) algorithm and its asymptotically-optimal counterpart called RRT* are popular algorithms used in real-life applications due to its desirable properties. Such algorithms are inherently iterative, but certain modules such as the collision-checking procedure can be parallelized providing significant speedup with respect to sequential implementations. In this paper, the RRT and RRT* algorithms have been adapted to a bioinspired computational framework called Membrane Computing whose models of computation, a.k.a. P systems, run in a non-deterministic and massively parallel way. A large number of robotic applications are currently using a variant of P systems called Enzymatic Numerical P systems (ENPS) for reactive controlling, but there is a lack of solutions for motion planning in the framework. The novel models in this work have been designed using the ENPS framework. In order to test and validate the ENPS models for RRT and RRT*, we present two ad-hoc implementations able to emulate the computation of the models using OpenMP and CUDA. Finally, we show the speedup of our solutions with respect to sequential baseline implementations. The results show a speedup up to 6x using OpenMP with 8 cores against the sequential implementation and up to 24x using CUDA against the best multi-threading configuration.

show abstract

“…These two requirements transform the TAM decision‐making problem into one of multi‐objective optimization (Bai, Ahmed, Li, & Labi, 2015; Šelih, Kne, Srdić, & Žura, 2008; Maggiore, Ford, High Street Consulting Group, & Burns & McDonnell, 2015). There are several broad approaches for solving multi‐objective optimization problems: non‐preference, priori preference articulation, interactive preference articulation, and posteriori preference articulation (Miettinen, 1999; Rodrigues, Papa, & Adeli, 2017). For example, Adey, Burkhalter, and Martani (2019) proposed a method that monetarily quantifies the impacts of infrastructure interventions and then maximizes the net benefit for all stakeholders to assist in TAM decision‐making.…”

Section: Introductionmentioning

confidence: 99%

Methodology for analyzing the trade‐offs associated with multi‐objective optimization in transportation asset management under uncertainty

Bai

Miralinaghi

Labi

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

Trade‐off analysis, one of the key tenets of multi‐objective optimization for the project selection problem in Transportation Asset Management (TAM), can help decision‐makers quantify and comprehend the consequences of different resource allocations in terms of the multiple measures of system performance. In analyzing TAM trade‐offs, it is vital to account duly for the uncertainties associated with these system‐wide performance measures. In this paper, we present a methodology that integrates chance‐constraint programming, the Lindeberg Central Limit Theorem, and a hybrid NSGA II method, to address the performance uncertainties associated with the TAM multi‐objective optimization problem. Through analyzing the trade‐offs between expenditure and performance, and between different performance measures, we generate Pareto frontiers at different confidence levels using a hybrid NSGA II method. We demonstrate the proposed methodology using a case study involving real‐life assets and the expected cost and performance benefits of projects associated with these assets. Regarding the trade‐off between cost and performance, we determine the extent to which the strengths of these relationships vary across different confidence levels. We find that, generally, for a given network performance level, a higher expenditure is needed to achieve a high confidence level compared to the expenditure needed to achieve a low confidence level, and more importantly, measures these sensitivities. This is the “Price of Confidence” concept. Regarding the trade‐off between different pairs of performance measures under budgetary constraints, we show how these relationships vary with the confidence level specified for the analysis, and we measure the extent to which higher confidence level requirements translate into lower levels of overall system‐wide performance.

show abstract

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

Cited by 35 publications

References 116 publications

A multi-aperture optical flow estimation method for an artificial compound eye

A multi-aperture optical flow estimation method for an artificial compound eye

A membrane parallel rapidly-exploring random tree algorithm for robotic motion planning

Methodology for analyzing the trade‐offs associated with multi‐objective optimization in transportation asset management under uncertainty

Contact Info

Product

Resources

About