Frequency of Conjunctivitis among Farmers of District Vehari, Punjab, Pakistan Conjuntivitis among farmers of Vehari

Conjunctivitis is a globally prevalent ocular and/eye infection. The basic motivation of the current study may be traced back to the association of conjunctivitis with unhygienic situations and sunlight exposure. The daily routine of farmers, overwhelming poverty, and illiteracy ratio may have further enhanced the incidence ratio of conjunctivitis. The ocular infection and/or conjunctivitis is caused by various pathogens, if not managed properly and appropriately may lead to corneal perforation or blindness. Objective: The study has been designed to find out the prevalence of various pathogenic and allergic conjunctivitis among farmers in the district Vehari, Punjab, Pakistan. Methods: It was a community-based and cross-sectional descriptive studyfrom October- November 2019. The study involved the quantitative analytical method. Anterior segments of eyes followed by posterior segments were examined by using an ophthalmoscope and torchlight for the diagnosisof conjunctivitis. Data on pathogenic and allergic conjunctiva was collected. Result: Our study indicated that 33(16.5%) farmers were found with the symptoms ascertained with conjunctivitis. Among the studied subjects, 29(14.5%) and 4(2%) farmers were found with bacterial and viral conjunctivitis, respectively. As far as the tendency of seeking medical help and ophthalmic consultation is concerned, 31(15.5%) and 19(9.5%) patients preferred to get examined by an eye specialist and traditional treatment, respectively. However, 150(75%) patients neglected to seek any medical aid. It was found 27 (13.5%), and 55 (27.5%) farmers were using glasses and traditional eye protective measures, respectively. However, almost sixty percent 118(59%) of farmers were not using any type of eye-protective measures. It was found that 59%, 30%, and 11% farmer population was exposed to sunlight for almost six, four, and two hours, respectively on daily basis. Conclusions: The use of prevalent traditional protective measures and lack of treatment or medical aid seeking trendby farmers has been found responsible for the high incidence of bacterial conjunctivitis. Moreover, long working hours and sunlight exposure alongwith the predominant unhygienic conditions may further quadruple the frequency of viral and bacterial conjunctivitis. The high prevalence ratio of conjunctivitis, eye infections, and ocular injuries highlight the need of observing universal eye safety and precautionary measures. Keeping in view the downtrodden economic conditions of the farmers and agriculturalists in the country and the financial repercussions associated with the infection, a state-ownedmedical awareness and relief process must be ensured and encouraged for the Pakistani community.

Classification and Associative Classification Rule Discovery Using Ant Colony Optimization

The primary goal of this research is to investigate the suitability of ant colony optimization, a swarm intelligence based meta-heuristic developed by mimicking some aspects of the food foraging behavior of ants, for building accurate and comprehensible classifiers which can be learned in reasonable time even for large datasets. Towards this end, a novel classification rule discovery algorithm called AntMiner-C and its variants are proposed. Various aspects and parameters of the proposed algorithms are investigated by experimentation on a number of benchmark datasets. Experimental results indicate that the proposed approach builds more accurate models when compared with commonly used classification algorithms. It is also computationally less expensive than previously available ant colony algorithm based classification rules discovery algorithms. A hybrid classifier using ant colony optimization is also proposed that combines association rules mining and supervised classification. Experiments show that the proposed algorithm has the ability to discover high quality rules. Furthermore, it has the advantage that association rules of each class can be mined in parallel if distributed processing is used. Experimental results demonstrate that the proposed hybrid classifier achieves higher accuracy rates when compared with other commonly used classification algorithms. A feature subset selection algorithm is also proposed which is based on ant colony optimization and decision trees. Experiments show that better accuracy is achieved if the subset of features selected by the proposed approach is used instead of full feature set and number of rules is also decreased substantially.