scholarly journals Environmental characterization of microhabitats used by amphibians in the Tensift region of Morocco: An explanatory assessment using Artificial Neural Networks

2020 ◽  
Author(s):  
Radouane Ait El Cadi ◽  
Tahar Slimani ◽  
Mohamed Aitbabram ◽  
El Hassan El Mouden
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Environmental Factors ◽  
High Performance ◽  
Principal Component ◽  
Amphibian Species ◽  
New Information ◽  
Adequate Understanding ◽  
Artificial Neural ◽  
Almost All

An adequate understanding of the relationship between amphibians and their habitat has been among the main challenges in herpetology in recent decades, particularly given the role of global change in the rapid declines of this group worldwide. Using the Artificial Neural Networks approach (ANN), we examined the environmental factors determining the occurrence of amphibians in the aquatic ecosystems in Tensift region of Morocco. We applied this modeling technique to 14 environmental factors and the presence of amphibian species collected from 40 sites. The results showed that the ANN is a useful approach to evaluate the effects of habitat factors on species occurrence. The model correctly classified all species with high performance. The best result was obtained for Bufo spinosus data, with a recognition percentage of 93.6% and a prediction performance of 99.4%. Of all factors studied, altitude was key in explaining the species distribution and richness, followed by hydroperiod and conductivity, for almost all species. The importance of other factors varied according to species. Principal Component Analysis differentiated a community composed by three species of Bufonidae (Bufotes boulengeri, Sclerophrys mauritanica and Barbarophryne brongersmai) that are close to Hyla meridionalis, while Bufo spinosus, Discoglossus scovazzi and Pelophylax saharicus were influenced by other environmental factors. The results provide important new information that will support conservation decision making for the protection of amphibian populations and their habitats in the studied region

Developing a Predictive Model for Plasmodium knowlesi–Susceptible Areas in Malaysia Using Geospatial Data and Artificial Neural Networks

2021 ◽  
pp. 101053952110486
Author(s):  
Rozita Hod ◽  
Siti Aisah Mokhtar ◽  
Farrah Melissa Muharam ◽  
Ummi Kalthom Shamsudin ◽  
Jamal Hisham Hashim
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Environmental Factors ◽  
Predictive Model ◽  
Land Surface ◽  
Plasmodium Knowlesi ◽  
Geospatial Data ◽  
Susceptibility Index ◽  
Malaria Susceptibility ◽  
Artificial Neural

Plasmodium knowlesi is an emerging species for malaria in Malaysia, particularly in East Malaysia. This infection contributes to almost half of all malaria cases and deaths in Malaysia and poses a challenge in eradicating malaria. The aim of this study was to develop a predictive model for P. knowlesi susceptibility areas in Sabah, Malaysia, using geospatial data and artificial neural networks (ANNs). Weekly malaria cases from 2013 to 2014 were used to identify the malaria hotspot areas. The association of malaria cases with environmental factors (elevation, water bodies, and population density, and satellite images providing rainfall, land surface temperature, and normalized difference vegetation indices) were statistically determined. The significant environmental factors were used as input for the ANN analysis to predict malaria cases. Finally, the malaria susceptibility index and zones were mapped out. The results suggested integrating geospatial data and ANNs to predict malaria cases, with overall correlation coefficient of 0.70 and overall accuracy of 91.04%. From the malaria susceptibility index and zoning analyses, it was found that areas located along the Crocker Range of Sabah and the East part of Sabah were highly susceptible to P. knowlesi infections. Following this analysis, targetted entomological mapping and malaria control programs can be initiated.

scholarly journals Artificial Neural Networks for Automated Cell Quantification in Lensless LED Imaging Systems

Proceedings ◽  
2018 ◽  
Vol 2 (13) ◽  
pp. 989 ◽  
Author(s):  
Agus Budi Dharmawan ◽  
Gregor Scholz ◽  
Shinta Mariana ◽  
Philipp Hörmann ◽  
Igi Ardiyanto ◽  
...  
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Artificial Neural Networks ◽  
Light Emitting Diode ◽  
Principal Component ◽  
Component Analysis ◽  
Detection Accuracy ◽  
Cell Detection ◽  
Artificial Neural ◽  
Feature Values

Cell registration by artificial neural networks (ANNs) in combination with principal component analysis (PCA) has been demonstrated for cell images acquired by light emitting diode (LED)-based compact holographic microscopy. In this approach, principal component analysis was used to find the feature values from cells and background, which would be subsequently employed as neural inputs into the artificial neural networks. Image datasets were acquired from multiple cell cultures using a lensless microscope, where the reference data was generated by a manually analyzed recording. To evaluate the developed automatic cell counter, the trained system was assessed on different data sets to detect immortalized mouse astrocytes, exhibiting a detection accuracy of ~81% compared with manual analysis. The results show that the feature values from principal component analysis and feature learning by artificial neural networks are able to provide an automatic approach on the cell detection and registration in lensless holographic imaging.

Knowledge Discovery with Artificial Neural Networks

2011 ◽  
pp. 669-673
Author(s):  
Juan R. Rabuñal Dopico ◽  
Daniel Rivero Cebrian ◽  
Julián Dorado de la Calle ◽  
Nieves Pedreira Souto
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Knowledge Discovery ◽  
Powerful Technique ◽  
Complex Problems ◽  
New Information ◽  
Wide Range ◽  
The World ◽  
Artificial Neural

The world of Data Mining (Cios, Pedrycz & Swiniarrski, 1998) is in constant expansion. New information is obtained from databases thanks to a wide range of techniques, which are all applicable to a determined set of domains and count with a series of advantages and inconveniences. The Artificial Neural Networks (ANNs) technique (Haykin, 1999; McCulloch & Pitts, 1943; Orchad, 1993) allows us to resolve complex problems in many disciplines (classification, clustering, regression, etc.), and presents a series of advantages that convert it into a very powerful technique that is easily adapted to any environment. The main inconvenience of ANNs, however, is that they can not explain what they learn and what reasoning was followed to obtain the outputs. This implies that they can not be used in many environments in which this reasoning is essential.

Sign in / Sign up

Export Citation Format

Share Document