Unsupervised land-cover classification through hyper-heuristic-based Harmony Search

Papa, João Paulo; Papa, Luciene Patrici; Pisani, Rodrigo José; Pereira, Danillo Roberto

doi:10.1109/igarss.2015.7325699

Cited by 2 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work proposed by Papa et al [25] goes beyond that point by combining different solutions obtained through distinct metaheuristic techniques. Since each technique has its own weaknesses, the idea is to explore a higher level of optimization in order to improve each individual solution by means of the combination of all obtained solutions so far.…”

Section: Optimizing K-means Through Hyperheuristicsmentioning

confidence: 99%

“…Mutation and crossover aim at allowing a greater variability to the population of individuals, while reproduction tries to maintain the best ones to the next generation. In short, mutation operations change each individual without considering others, i.e., given a mutation point, we can simply generate a new random [25]. The function node "SUM" stands for "summation," "DIV" denotes the "division" operator, "EXP" stands for the "exponentiation," and "LOG" corresponds to the "logarithm."…”

Section: Optimizing K-means Through Hyperheuristicsmentioning

confidence: 99%

“…1 That work employed genetic programming to combine five variations of the HS algorithm with promising results. In this paper, we extend the work by Papa et al [25] with a deeper experimental analysis, in which PSO, bat algorithm (BA), and firefly algorithm (FFA) are also considered together with HS and its variants for combination purposes through genetic programming. The results obtained in this paper outperformed the previous work by Papa et al [25], thus emphasizing the benefits of the hyper-heuristic-based framework.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we extend the work by Papa et al [25] with a deeper experimental analysis, in which PSO, bat algorithm (BA), and firefly algorithm (FFA) are also considered together with HS and its variants for combination purposes through genetic programming. The results obtained in this paper outperformed the previous work by Papa et al [25], thus emphasizing the benefits of the hyper-heuristic-based framework. To the best of our knowledge, that is the first time such approaches are combined with each other aiming at optimizing k-means.…”

Section: Introductionmentioning

confidence: 99%

“…The term "hyperheuristics" was coined to address new algorithms designed to solve general problems by combining known metaheuristics, in such a way each technique may compensate the weaknesses of others [24]. In such context, Papa et al [25] were one of the first that focused on the application of hyperheuristics to optimize k-means, being the proposed approach validated in the background of both satellite-and radarbased land-cover classification. 1 That work employed genetic programming to combine five variations of the HS algorithm with promising results.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Hyperheuristic Approach for Unsupervised Land-Cover Classification

Papa

Pereira

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Unsupervised land-use/cover classification is of great interest, since it becomes even more difficult to obtain high-quality labeled data. Still considered one of the most used clustering techniques, the well-known k-means plays an important role in the pattern recognition community. Its simple formulation and good results in a number of applications have fostered the development of new variants and methodologies to address the problem of minimizing the distance from each dataset sample to its nearest centroid (mean). In this paper, we present a genetic programmingbased hyperheuristic approach to combine different metaheuristic techniques used to enhance k-means effectiveness. The proposed approach is evaluated in four satellite and one radar image showing promising results, while outperforming each individual metaheuristic technique.

show abstract

Section: Optimizing K-means Through Hyperheuristicsmentioning

confidence: 99%

Section: Optimizing K-means Through Hyperheuristicsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Hyperheuristic Approach for Unsupervised Land-Cover Classification

Papa

Pereira

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

Impact of Land Use and Land Cover Changes on Urban Ecosystem Service Value in Dhaka, Bangladesh

Rahman

Szabó

2021

Land

View full text Add to dashboard Cite

Urban ecosystem services provide a wide range of services to sustain life, social relation, health, etc., and address most of the challenges, including climate change and environmental pollution. While it is recognized that the urban ecosystem substantially contributes to human well-being in cities, there is less attention to consider the value of urban ecosystem service in urban planning and policymaking. This study analyzed the land use and land cover (LULC) dynamics of city of Dhaka over the past three decades (1990–2020) to evaluate the impact of LULC on ecosystem services value (ESV). The estimation of ESV in relation to LULC has been done using the globally used benefits transfer method (BTM). Findings of the study show that built-up area has increased by 188.35% from 1990 to 2020, with an average annual growth rate is about 6.28%. The analysis of ESV shows that it has decreased by 59.55% (85 million USD) from 142.72 million USD in 1990 to 57.72 million USD in 2020 due to the development of the built-up area through conversion of agricultural land, waterbodies, and forest and vegetation land. This study also identified that waterbodies are the greatest contributor to ESV. The result on the elasticity of ESV in relation to LULC implies that about 1% transition in LULC would result in about 0.33% change in total ESV during the study period. We believe that the findings of this study would serve as a reference for the policy maker and urban planner to devise appropriate land use decision to ensure sustainable urban development of Dhaka.

show abstract

Unsupervised land-cover classification through hyper-heuristic-based Harmony Search

Cited by 2 publications

References 13 publications

A Hyperheuristic Approach for Unsupervised Land-Cover Classification

A Hyperheuristic Approach for Unsupervised Land-Cover Classification

Impact of Land Use and Land Cover Changes on Urban Ecosystem Service Value in Dhaka, Bangladesh

Contact Info

Product

Resources

About