Development of a memetic algorithm for Dynamic Multi-Objective Optimization and its applications for online neural network modeling of UAVs

Isaacs, Amitay; Puttige, Vishwas; Ray, Tapabrata; Smith, Warren; Anavatti, Sreenatha G.

doi:10.1109/ijcnn.2008.4633847

Cited by 23 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, using the FDA1 DMOOP alone to test whether an algorithm can solve DMOOPs is not sufficient. Mehnen et al 2006;Zeng et al 2006;Bingul 2007;Cámara et al 2007aCámara et al , 2007bZheng 2007;Zhou et al 2007;Greeff and Engelbrecht 2008;Isaacs et al 2008;Tan and Goh 2008;Wang and Dang 2008;Chen et al 2009;Tan 2009b, 2009a;Lechuga 2009;Wang and Li 2009;Cámara et al 2009Cámara Sola 2010;Greeff and Engelbrecht 2010;Koo et al 2010;Wang and Li 2010; Engelbrecht 2011] Modified [Zhou et al 2007] FDA2…”

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

“…Original [Farina et al 2004;Zeng et al 2006;Cámara et al 2007aCámara et al , 2007bLiu and Wang 2007;Wang and Dang 2008;Greeff and Engelbrecht 2010;Liu 2010;Wang and Li 2010; Engelbrecht 2011] Modified [Mehnen et al 2006;Deb et al 2007;Zheng 2007;Isaacs et al 2008;Lechuga 2009;Cámara et al 2009Cámara Sola 2010; [Mehnen et al 2006;Liu and Wang 2007;Tan 2009b, 2009a;Wang and Li 2009;Koo et al 2010;Liu 2010;Wang and Li 2010;Helbig and Engelbrecht 2011] Several researchers have used the FDA2 DMOOP. However, the POF of FDA2 changes from a convex to a concave shape only for specific values of the decision variables [Mehnen et al 2006;Deb et al 2007], as can be seen, for example, in Engelbrecht [2011, 2013b].…”

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

“…Therefore, even if an algorithm finds Pareto-optimal solutions, it may find a convex POF instead of a concave POF. To address this issue, several modifications to the h or g function of FDA2 have been suggested [Cámara et al 2009Deb et al 2007;Isaacs et al 2008;Lechuga 2009;Mehnen et al 2006;Cámara Sola 2010;Zheng 2007]. Underlying problems with FDA3 also lead to several modifications to FDA3 being suggested Zheng 2007].…”

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

“…DMOOPs with an isolated or deceptive POF are [Zheng 2007;] -Type III: dMOP1 (Equation (13)) -DMOOPs with a nonconvex POF -Type I: DMZDT2 [Wang and Li 2009], FDA4 (Equation (8)), DMOP3 ] -Type II: FDA5 (Equation (9) (19)), HE2 (Equation (20)) -DMOOPs with a nonuniform spread of solutions -Type I: dMOP3 (Equation (15)) -Type II: FDA5 (Equation (9)), modified FDA3 functions [Zheng 2007;] -Type III: Modified FDA5 3. DMOOPs with various types or shapes of POSs -Types I, II: DTLZ Av (Equation (21)) -Type II: ZJZ (Equation (16)), DSW2 (Equation (28)), DSW3 (Equation (29)) -Type III: HE3 to HE10 (Equations (34) through (41)) -Types II, III: Modified FDA2 [Mehnen et al 2006;Deb et al 2007;Zheng 2007;Isaacs et al 2008;Lechuga 2009;Cámara et al 2009Cámara Sola 2010] 4. DMOOPs with dependencies between the decision variables -Type II: ZJZ (Equation (16)) c 2013 IEEE.…”

Section: Evaluation Of Dmoo Algorithmsmentioning

confidence: 99%

“…Selecting which performance (9)), modified FDA3 functions [Zheng 2007;] -Type III: Modified FDA5 2. DMOOPs where the POF changes from convex to nonconvex and/or vice versa over time -Type II: dMOP2 (Equation (14)), ZJZ (Equation (16)) -Type III: dMOP1 (Equation (13)) -Types II, III: Modified FDA2 functions [Mehnen et al 2006;Deb et al 2007;Zheng 2007;Isaacs et al 2008;Lechuga 2009;Cámara et al 2009Cámara Sola 2010] 3. DMOOPs where the shape of POS changes over time -Various types: DTLZ Av (refer to Equation (21)) 4.…”

Section: Evaluation Of Dmoo Algorithmsmentioning

confidence: 99%

See 4 more Smart Citations

Benchmarks for dynamic multi-objective optimisation algorithms

Helbig

Engelbrecht

2014

ACM Comput. Surv.

View full text Add to dashboard Cite

Algorithms that solve Dynamic Multi-Objective Optimisation Problems (DMOOPs) should be tested on benchmark functions to determine whether the algorithm can overcome specific difficulties that can occur in real-world problems. However, for Dynamic Multi-Objective Optimisation (DMOO), no standard benchmark functions are used. A number of DMOOPs have been proposed in recent years. However, no comprehensive overview of DMOOPs exist in the literature. Therefore, choosing which benchmark functions to use is not a trivial task. This article seeks to address this gap in the DMOO literature by providing a comprehensive overview of proposed DMOOPs, and proposing characteristics that an ideal DMOO benchmark function suite should exhibit. In addition, DMOOPs are proposed for each characteristic. Shortcomings of current DMOOPs that do not address certain characteristics of an ideal benchmark suite are highlighted. These identified shortcomings are addressed by proposing new DMOO benchmark functions with complicated Pareto-Optimal Sets (POSs), and approaches to develop DMOOPs with either an isolated or deceptive Pareto-Optimal Front (POF). In addition, DMOO application areas and real-world DMOOPs are discussed.

show abstract

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

Section: Dmoo Benchmark Functions Currently Usedmentioning

confidence: 99%

Section: Evaluation Of Dmoo Algorithmsmentioning

confidence: 99%

Section: Evaluation Of Dmoo Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

Benchmarks for dynamic multi-objective optimisation algorithms

Helbig

Engelbrecht

2014

ACM Comput. Surv.

View full text Add to dashboard Cite

show abstract

Differential Evolution and Offspring Repair Method Based Dynamic Constrained Optimization

Pal

Saha

Das

2013

Swarm, Evolutionary, and Memetic Computing

View full text Add to dashboard Cite

A predictive strategy based on special points for evolutionary dynamic multi-objective optimization

Zou

Yang

et al. 2018

Soft Comput

View full text Add to dashboard Cite

There are some real-world problems in which multiple objectives conflict with each other and the objectives change with time. These problems require an optimization algorithm to track the moving Pareto front or Pareto set over time. In this paper, we propose a predictive strategy based on special points (SPPS) which consists of three mechanisms. The first one is that the non-dominated set is predicted directly by feed-forward center points, which can eliminate many useless individuals predicted by traditional prediction using feed-forward center points. The second one is that a special point set(such as boundary point, knee point, etc.) is introduced into the predicted population which can track Pareto front or Pareto set more accurately. The third one is the adaptive diversity maintenance mechanism based on boundary points and center points. The mechanism can introduce diverse individuals of the corresponding number according to the degree of difficulty of the problem to keep the diversity of the population. The number of these diverse individuals is strongly related to the center points. Then, they are generated evenly throughout the decision space between the boundary points. The proposed strategy is

show abstract

Development of a memetic algorithm for Dynamic Multi-Objective Optimization and its applications for online neural network modeling of UAVs

Cited by 23 publications

References 12 publications

Benchmarks for dynamic multi-objective optimisation algorithms

Benchmarks for dynamic multi-objective optimisation algorithms

Differential Evolution and Offspring Repair Method Based Dynamic Constrained Optimization

A predictive strategy based on special points for evolutionary dynamic multi-objective optimization

Contact Info

Product

Resources

About