Self-organizing map (SOM) for species distribution modelling of birds species at Kenyir landscape

Identifying which biodiversity species are more dominant than others in any area is a very challenging task. This is because of the abundant of biodiversity species that may become the majority species in any particular region. This situation create a large dataset with a complex variables to be analysed. Moreover, the responds of organisms and environmental factors are occurred in a non-linear correlation. The effort to do so is really important in order to conserve the biodiversity of nature. To understand the complex relationships that exist between species distribution and their habitat, we analysed the interactions among bird diversity, spatial distribution and land use types at Kenyir landscape in Terengganu, Malaysia by using artificial neural network (ANN) method of self-organizing map (SOM) analysis. SOM performs an unsupervised and non-linear analysis on a complex and large dataset. It is capable to handle the non-linear correlation between organism and environmental factors because SOM identifies clusters and relationships between variables without the fixed assumptions of linearity or normality. The result suggested that SOM analysis was suited for understanding the relationships between bird species assemblages and habitat characteristics.

Download Full-text

Factors affecting the species richness and composition of bird species in a community managed forest of Nepal

Journal of Threatened Taxa ◽

10.11609/jott.6945.13.9.19212-19222 ◽

2021 ◽

Vol 13 (9) ◽

pp. 19212-19222

Author(s):

Bishow Poudel ◽

Bijaya Neupane ◽

Rajeev Joshi ◽

Thakur Silwal ◽

Nirjala Raut ◽

...

Keyword(s):

Diversity Index ◽

Bird Species ◽

Habitat Characteristics ◽

Lower Percentage ◽

Bird Diversity ◽

Limited Information ◽

Managed Forest ◽

Point Count ◽

Community Forests ◽

Wiener Diversity Index

There exists limited information on biodiversity including avifaunal diversity and habitat condition in community forests (CF) of Nepal; thus we aimed to fulfill such gaps in Tibrekot CF of Kaski district. We used the point count method for assessing bird diversity and laid out a circular plot size of radius 5-m within 15-m distance from each point count station for recording the biophysical habitat characteristics. Bird species’ diversity, richness and evenness were calculated using popular indexes and General Linear Model (GLM) was used to test the respective effect of various biophysical factors associated with the richness of bird species. In total, 166 (summer 122, winter 125) bird species were recorded in 46 sample plots. The Shannon-Wiener diversity index was calculated as 3.99 and 4.09, Margalef’s richness index as 16.84 and 17.53 and Pielou’s evenness index as 0.83 and 0.84 for summer and winter, respectively. The influencing factors for richness of bird species were season (χ21, 90= 112.21; P= 0.016) with higher richness in the summer season and low vegetation cover (χ21, 89= 113.88; P= 0.0064) with higher richness in lower percentage cover. Thus, community managed forest should be protected as it has a significant role in increasing bird diversity, which has potential for attracting avifaunal tourism for the benefit of the local communities.

Download Full-text

Scene Oriented Classification of Blurry and Noisy Images Using SVM with Fuzzy C Mean Clustering

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY ◽

10.24297/ijct.v12i4.3186 ◽

2014 ◽

Vol 12 (4) ◽

pp. 3393-3402

Author(s):

Deepak Nema

Keyword(s):

Support Vector Machine ◽

Hierarchical Clustering ◽

Hierarchical Classification ◽

Computation Time ◽

Support Vector ◽

Self Organizing Map ◽

Large Dataset ◽

Noisy Images ◽

Self Organizing

Image classification is a challenging task in image processing especially in the case of blurry and noisy images. In this work, we present an extension of scene oriented hierarchical classification of blurry and noisy images using Support Vector Machine (SVM) and Fuzzy C-Mean. Generally, a system for scene-oriented classification of blurry and noisy images attempts to simulate major features of the human visual observation. These approaches areÂ based on three strategies such as Global pathway for extracting essential signature of image, local pathway for extracting local features, and then outcome of both global and local phase are combined and define feature vector and clustered using Monte Carlo approach. Afterwards, these clustered results are fed to a SOTA Algorithm (combination of self organizing map and hierarchical clustering) for final classification. But in these approaches, combination of self organizing map and hierarchical clustering has the problem in terms of accuracy and computation time of classification, especially when used large dataset for classification. To overcome this problem, we propose a combination of Support Vector Machine (SVM) and Fuzzy C-mean. Our proposed approach provides better result in terms of accuracy, especially when used with large dataset. The proposed method is computationally efficient because fuzzy c-mean clustering is faster and less time consuming as compared to hierarchical clustering.

Download Full-text

Enhancing Performance of Parallel Self-Organizing Map on Large Dataset with Dynamic Parallel and Hyper-Q

Data Science Journal of Computing and Applied Informatics ◽

10.32734/jocai.v2.i2-324 ◽

2018 ◽

Vol 2 (2) ◽

pp. 62-73

Author(s):

Alexander F.K. Sibero ◽

Opim Salim Sitompul ◽

Mahyuddin K.M. Nasution

Keyword(s):

Graphics Processing Unit ◽

Computing Time ◽

Computation Time ◽

Processing Unit ◽

Self Organizing Map ◽

Large Dataset ◽

Time Dynamic ◽

Neural Network Algorithm ◽

Graphics Processing ◽

Self Organizing

Self-Organizing Map (SOM) is an unsupervised artificial neural network algorithm. Even though this algorithm is known to be an appealing clustering method,many efforts to improve its performance are still pursued in various research works. In order to gain faster computation time, for instance, running SOM in parallel had been focused in many previous research works. Utilization of the Graphics Processing Unit (GPU) as a parallel calculation engine is also continuously improved. However, total computation time in parallel SOM is still not optimal on processing large dataset. In this research, we propose a combination of Dynamic Parallel and Hyper-Q to further improve the performance of parallel SOM in terms of faster computing time. Dynamic Parallel and Hyper-Q are utilized on the process of calculating distance and searching best-matching unit (BMU), while updating weight and its neighbors are performed using Hyper-Q only. Result of this study indicates an increase in SOM parallel performance up to two times faster compared to those without using Dynamic Parallel and Hyper-Q.

Download Full-text

SENSITIVITY ANALYSIS FOR NON-LINEAR SYSTEM USING SELF-ORGANIZING MAP

PROCEEDINGS OF HYDRAULIC ENGINEERING ◽

10.2208/prohe.51.289 ◽

2007 ◽

Vol 51 ◽

pp. 289-294 ◽

Cited By ~ 1

Author(s):

Yoshihiko ISERI ◽

Kenji JINNO ◽

Daiki SATOMURA ◽

Bellie SIVAKUMAR ◽

Koji NISHIYAMA

Keyword(s):

Sensitivity Analysis ◽

Linear System ◽

Self Organizing Map ◽

Non Linear ◽

Non Linear System ◽

Self Organizing

Download Full-text

Bird diversity in an urban ecosystem: the role of local habitats in understanding the effects of urbanization

Iheringia Série Zoologia ◽

10.1590/1678-4766e2018017 ◽

2018 ◽

Vol 108 (0) ◽

Cited By ~ 5

Author(s):

Aline Goulart Rodrigues ◽

Márcio Borges-Martins ◽

Felipe Zilio

Keyword(s):

Urban Planning ◽

Species Distribution ◽

Vegetation Cover ◽

Urban Areas ◽

Bird Species ◽

Species Assemblages ◽

Bird Diversity ◽

Noise Levels ◽

Habitat Features ◽

Green Areas

ABSTRACT: Urbanization causes environment changes that directly affect biotic diversity, and understanding the relationship between fauna and urban features is a key aspect of urban planning. Birds are particularly affected by urbanization. Noise levels, for instance, negatively affect birds’ behavior and social communication, while the presence of green areas promotes bird diversity. The effects of urbanization could differ according with the level of urbanization, and our goal was to understand how bird species assemblages are related to urban features in an intermediate stage of urbanization (a city in Brazil with 2,470 inhabitants/km²). We used canonical correspondence analysis (CCA) and generalized linear models (GLM) analyses to assess how bird species assemblages are affected by urban features (e.g., noise level, abundance of buildings) as well as habitat features (e.g., vegetation cover). Despite we did not find a clear pattern of urbanization both the urban and habitat features had, even if weak, an effect on bird species distribution. Bird species distribution was spatially correlated, and we identified three groups: 1) grassland and wetland species; 2) forest species; 3) species tolerant to habitat degradation. Species richness was positively related to the proportion of trees, abundance of people and presence of buildings, and negatively affected by higher levels of noise. The abundance of species decreased as noise levels increased, but the proportion of green areas (open or forest vegetation) had a positive effect. Agreeing with previous research, our study shows that noise levels and vegetation cover seem to be the best predictors of diversity in urban areas. Nevertheless, the presence of particular habitats (wetlands, grasslands, woodlots), patchily distributed in the urban matrix, could buffer the effects of urbanization on birds. These habitats should thus be taken into account in urban planning.

Download Full-text

Erosion of tropical bird diversity over a century is influenced by abundance, diet and subtle climatic tolerances

Scientific Reports ◽

10.1038/s41598-021-89496-7 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Jenna R. Curtis ◽

W. Douglas Robinson ◽

Ghislain Rompré ◽

Randall P. Moore ◽

Bruce McCune

Keyword(s):

Human Disturbance ◽

Bird Species ◽

Bird Communities ◽

Habitat Characteristics ◽

Barro Colorado Island ◽

Bird Diversity ◽

Species Assemblage ◽

Forest Fragment ◽

Rainfall Gradient ◽

Dietary Preferences

AbstractHuman alteration of landscapes leads to attrition of biodiversity. Recommendations for maximizing retention of species richness typically focus on protection and preservation of large habitat patches. Despite a century of protection from human disturbance, 27% of the 228 bird species initially detected on Barro Colorado Island (BCI), Panama, a large hilltop forest fragment isolated by waters of Gatun Lake, are now absent. Lost species were more likely to be initially uncommon and terrestrial insectivores. Analyses of the regional avifauna, exhaustively inventoried and mapped across 24 subregions, identified strong geographical discontinuities in species distributions associated with a steep transisthmian rainfall gradient. Having lost mostly species preferring humid forests, the BCI species assemblage continues to shift from one originally typical of wetter forests toward one now resembling bird communities in drier forests. Even when habitat remnants are large and protected for 100 years, altered habitat characteristics resulting from isolation produce non-random loss of species linked with their commonness, dietary preferences and subtle climatic sensitivities.

Download Full-text