Precise plant classification within genus level based on simulated annealing aided cloud classifier
Research highlights
► Series application research of improved cloud classifier algorithm. ► Annealing algorithm combined with the cloud classifier. ► Simulated annealing to minimize the edge distances.
Introduction
Cloud theory is now a popular theory handling uncertainty based on the uncertain transition between qualitative concept and quantitative description (Li et al., 1998, Li et al., 1997, Li et al., 1998). Based on this theory, the cloud classifier has been developed recent years for adaptive linguistic hedge (Lu, Pi, Peng, Wang, & Zhang, 2009). This classifier represents a qualitative concept with three digital characteristics, expected value Ex, entropy σ and deviation D (Di et al., 1998a, Di et al., 1998b), which integrates the fuzziness and randomness of a linguistic term in a unified way. Our previously work (Lu et al., 2009) applied this classifier in the plant numerical taxonomy. In which, the particle swarm optimization algorithm (PSO) was used for optimizing the sections’ hedges. However, there is still some potential improvement left for us as the accurate rates is not high enough. In this work, we will apply the shortest path based simulated annealing algorithm (SPSA) in optimizing the cloud classifier.
SPSA is a new kind of dynamic multi-stage facility layout problem under dynamic business environment, in which new species may be added into, or old species may be removed from their original taxa. Since every section (or genus) has its own range, the distances of species to their ‘expected species’ (Lu et al., 2009) in each section (or genus) should get the global minimum values before the best classification being gained (Pi et al., 2009). Then, the hedges problem could be converted into a shortest path problem by studying its distance function and species adding/removing heuristic rules, and the corresponding mathematical model established for this problem (Dong, Wu, & Hou, 2009). Hence, the SPSA may have good performances in optimizing the cloud classifier.
In this research, the shortest path based simulated annealing aided cloud classifier (SPSACM) method is used for plant classification by analyzing leaf morphology and anatomy data which is partly from our previous work (Lin et al., 2008, Lu et al., 2008). Our purpose is to provide a basic tool in plant taxonomy.
Section snippets
Materials
Adult leaves fully exposed to sunlight of plants of the genus Camellia are collected from the International Camellia Species Garden in Jinhua city, including 15 species in Section Paracamellia Sealy: Camellia grijsii Hance, Camellia confuse Craib, Camellia kissi Wall., Camellia fluviatilis Hand.-Mazz., Camellia brevistyla Coh. St., Camellia hiemalis Nakai, Camellia obtusifolia Chang, Camellia maliflora Lindl, Camellia shensiensis Chang, Camellia puniceiflora Chang, Camellia tenii Sealy,
Different classification results based on different attributes
Fig. 2A shows a 3-D (based on three selective attributes) distribution of original data. After the classification procedure, Fig. 2B and C shows visible differences in the cloud models with different attribute base. Fig. 2D displays all available linguistic atoms generated by a series of linguistic atom generators in this research. These generators have different rules for analysis of quantity and qualitative data.
Cloud models in Fig. 2B, which are based on attributes with small weights (CMSW)
Discussion
In the plant numerical taxonomy, floras are used as most comprehensive tools for people to identify and distinguish plants (Brach & Song, 2005). Recent years, floras of large scope have been written by collaboration of many authors who collectively have examined thousands of plant samples and evaluated and incorporated information from dozens, or even hundreds, of publications (Wen, 1994). For the botanists edited these floras, two primary issues must be well considered: I. How should the
Conclusion
The proposed SPSACM method, based on attribute similarity, is extended from the cloud model and simulated annealing algorithm. We have firstly demonstrated by experiments that the taxonomic results based on the SPSACM method have shown the superiority performance over some related methods.
Then, the weight values of attributes are highly commended in establishing of flora keys.
Besides, we propose again the new nomenclature ‘expected species’: an included species that has the minimum sum of
Acknowledgements
The authors would like to thank Y.F. Huang and L.J. Ma for substantial help in data collection. Funding of Innovation Fund for the Master’s Academe of Zhejiang Normal University is also gratefully acknowledged.
References (26)
- et al.
Shortest path based simulated annealing algorithm for dynamic facility layout problem under dynamic business environment
Expert Systems with Applications
(2009) - et al.
Knowledge representation and discovery based on linguistic atoms
Knowledge-based Systems
(1998) - et al.
A particle swarm optimization-aided fuzzy cloud classifier applied for plant numerical taxonomy based on attribute similarity
Expert Systems with Applications
(2009) - et al.
Phylogenetic relationships and species circumscription in Trentepohlia and Printzina (Trentepohliales, Chlorophyta)
Molecular Phylogenetics and Evolution
(2009) - et al.
ActKey: A Web-based interactive identification key program
Taxon
(2005) - et al.
eFloras: New directions for online floras exemplified by the Flora of China Project
Taxon
(2006) - Chang, H. T. (1998). Theaceae. In Delectis Florae Reipublicae Popularis Sinicae Agendae Academiae Sinicae Edita (Ed.),...
A general system for coding taxonomic information
Taxon
(1980)A comparison of matrix-based taxonomic identification systems with rule-based systems
- Dallwitz, M. J., Paine, T. A., & Zurcher, E. J. (2000). Principles of interactive keys....
Knowledge representation and discovery in spatial databases based on cloud theory
International Archives of Photogrammetry and Remote Sensing
Intelligent query in spatial databases based on cloud model
Cited by (6)
Cloud computing research: A review of research themes, frameworks, methods and future research directions
2018, International Journal of Information ManagementCitation Excerpt :The final theme concerns the domains in which cloud computing has been applied. The articles in this theme investigate the application of cloud computing in areas such as education (Le Roux & Evans, 2011; Sultan, 2010), e-Science (Pi et al., 2011), e-Government (Decman & Vintar, 2013; Zissis and Lekkas, 2012), green IT (Basmadjian, Meer, Lent, & Giuliani, 2012; Gottschalk & Kirn, 2013), mobile cloud computing (Fernando, Loke, & Rahayu, 2013; Thilakanathan et al., 2014) and knowledge management (Lai, Tam, & Chan, 2012; Sultan, 2013). The studies acknowledge the positive transformation cloud computing has brought to these domains.
Camellia (Theaceae) classification with support vector machines based on fractal parameters and red, green, and blue intensity of leaves
2017, Bangladesh Journal of Plant TaxonomyA novel method of uncertain data classification
2014, Journal of Computational Information SystemsFloral morphology resolves the taxonomy of Camellia L. (Theaceae) sect. Oleifera and sect. Paracamellia
2012, Bangladesh Journal of Plant Taxonomy