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.

WHO water quality standards Vs Synergic effect(s) of fluoride, heavy metals and hardness in drinking water on kidney tissues.

Abstract: Despite WHO standards, waterborne diseases among the human being are rising alarmingly. It is known that the prolong exposure to contaminated water has major impact on public health. The effect of chemical contaminations in drinking water on human being is found to be chronic rather than acute and hence can be defined “consumption of contaminated drinking water could be a silent killer”. As the WHO recommended water quality standards are only for individual element and synergic effects of trace metals and anions have not been considered, investigation of synergic effects of trace metals and anions and their effect on human being is of prime important research. By an animal trial, we investigated the synergic effect(s) of heavy metals, aluminium, arsenic, fluoride and hardness in drinking water on kidney tissues of mice. Our investigation strongly suggests existing of a synergic effect especially among Cd, F and hardness of water which could lead to severe kidney damage in mice, even at WHO maximum recommended levels. Hence, the synergic effect(s) of trace metals, fluoride and hardness present in drinking water should be investigated meticulously when stipulating the water quality at WHO maximum recommended levels.

Automated Detection and Classification of Oral Lesions Using Deep Learning for Early Detection of Oral Cancer

Abstract: Oral cancer is a major global health issue accounting for 177,384 deaths in 2018 and it is most prevalent in low- and middle-income countries. Enabling automation in the identification of potentially malignant and malignant lesions in the oral cavity would potentially lead to low-cost and early diagnosis of the disease. Building a large library of well-annotated oral lesions is key. As part of the MeMoSA ® (Mobile Mouth Screening Anywhere) project, images are currently in the process of being gathered from clinical experts from across the world, who have been provided with an annotation tool to produce rich labels. A novel strategy to combine bounding box annotations from multiple clinicians is provided in this paper. Further to this, deep neural networks were used to build automated systems, in which complex patterns were derived for tackling this difficult task. Using the initial data gathered in this study, two deep learning based computer vision approaches were assessed for the automated detection and classification of oral lesions for the early detection of oral cancer, these were image classification with ResNet-101 and object detection with the Faster R-CNN. Image classification achieved an F1 score of 87.07% for identification of images that contained lesions and 78.30% for the identification of images that required referral. Object detection achieved an F1 score of 41.18% for the detection of lesions that required referral. Further performances are reported with respect to classifying according to the type of referral decision. Our initial results demonstrate deep learning has the potential to tackle this challenging task.

Ageing of silicone rubber insulators in coastal and inland tropical environment

Abstract: This paper presents investigations on the performance of 33 kV silicone rubber insulators characterized by different creepage lengths, which aimed to find out whether the insulators could permanently work when electrically stressed beyond the recommended limits in polluted and clean tropical environments. The study was performed under natural field and laboratory conditions. The insulators tested included eight types of silicone rubber composite insulators, one type of hybrid silicone-ceramic insulator and one semi-conducting glazed porcelain insulator, while ordinary porcelain and glass insulators were used as reference. During the field investigation, two sets of the insulators were separately installed and energized in coastal and inland parts of Sri Lanka, being by that exposed to marine and clean tropical environments. Their performances were periodically evaluated by visual inspections and measurements of hydrophobicity class. After five years of field exposure, the insulator performances were evaluated in laboratory by measurements of leakage currents under clean fog conditions and of wet flashover voltage. A third set of the insulators was aged in laboratory for 1000 hours inside a salt fog chamber where the insulators were continuously energized and daily sprayed with salt solution for eight hours and left to rest for remaining 16 hours. This treatment represented conditions similar as those in the field i.e. insulators exposed to salt sprays during monsoons. The insulator performances were investigated by measurements of leakage currents and classifying their patterns into different categories, i.e. capacitive, resistive, non-linear, discharge and strong discharge types, by means of fast Fourier transform and short time Fourier transform analyses. It was found that the long-term field exposure yielded weaker insulator deterioration than the salt fog chamber ageing, which indicated for a possibility to increase the electric stress on silicone rubber insulators to levels higher than the ones used today on glass and porcelain counterparts.