University of Peradeniya

About: University of Peradeniya is a education organization based out in Kandy, Sri Lanka. It is known for research contribution in the topics: Population & Poison control. The organization has 5970 authors who have published 7388 publications receiving 197002 citations.

Rice Fields: an Ecosystem Rich in Biodiversity

Abstract: Rice fields have been in existence since th'e beginning of organized agriculture. Since then a rich biodiversity has become associated with rice fields. Rice fields constitute manmade ecosystems. Due to their long existence, the vast extent of land they occupy in the humid tropics, the array of ccological habitats they encompass and the dilkrem phases they pass through during a cultivation cycle, rice fields have become unique ecosystems. It is an ecosystemthat sustains not only the people whose staple &et is rice but also a diverse assemblage of plants and animals that have made rice fields their niche. Rice fields are dynamic and rapidly changing ecosystems. The varied agronomic practices conducted on rice fields andthe series of growth stages the rice crop passes through during a short passage of time, have made rice fields a haven for a vast array of plant and animal life. To these life forms the rice fields offer shelter, food, breeding and nesting grounds. The rice fields also offer temporary refuge to those animals that are not permanent inhabitants but visit this ecosystem for avariety of purposes.

A sophisticated convolutional neural network model for brain tumor classification

Abstract: Magnetic Resonance Imaging(MRI) is one of the commonly used medical imaging modality that provides informative data for brain tumor diagnosis other than Computed Tomography(CT). A key challenge when a physician studies the MRI data is the time and effort he has to put in diagnosing the tumors. The objective of this research is to recognize the tumor type when a collection of MRI images of a patient is given. To achieve this goal, a deep learning algorithm is developed using Convolutional Neural Networks(CNNs). Nowadays, most of image classification problems use CNNs as they deliver higher precision and accuracy compared to other existing algorithms. Here, a sophisticated CNN model is developed, trained using cross validation and tested on brain MRI images obtained from open databases. The performance of the proposed model is promising.

Maternal Anthropometry as a Predictor of Birth Weight

Abstract: Maternal nutritional status is closely associated with birth weight of the newborn and perinatal morbidity and mortality. The usefulness of maternal anthropometric parameters i.e. maternal weight (WT), maternal height (HT) and maternal body mass index (BMI) as predictors of low birth weight (LBW) was studied in 563 full term babies selected from 2056 singleton live births. The sample included normotensive adult pregnant women who had their first visit to the clinics ≤13 weeks of gestation. Most of the pregnant mothers (80%) were between 20 and 34 years of age. Over one third of the mothers were nulliparous, while 12% were multiparous (parity ≥4). The incidence of LBW was 8.7% among the studied sample. The mean WT, HT and BMI of the sample were 53 kg, 155 cm and 22 kgm-2 respectively. Significant positive correlations were observed with birth weight (BW) and WT (r=0.27), BW and BMI (r=0.24) and BW and HT (r=0.11). Polynomial regression analysis predicted LBW significantly with the critical limits of WT, HT and BMI at 50.3 kg, 154 cm and 21.1 kgm -2 , with the sensitivity of 54%, 45% and 60% respectively. Logistic regression analysis showed the risk ratio (RR) for critical limits. Mothers with low WT ( -2 ) showed 1.5, 1.4 and 1.8 fold LBW respectively than mothers having values above the cut-off. At the highest sensitivity of 80% WT, HT and BMI have a RR of 1.8, 0.9 and 2.1 respectively but only the BMI reached a significant level. The best predictor of birth weight with 80% sensitivity was BMI of 23.7 kgm -2 at or below 13 weeks of gestation. DOI: http://dx.doi.org/10.4038/tar.v21i1.2590 Tropical Agricultural Research Vol. 21(1): 89-98 (2009)