http://ir.lib.seu.ac.lk/handle/123456789/6395 2021 2026-04-11T22:28:58Z http://ir.lib.seu.ac.lk/handle/123456789/6617 Title: Table of contents 2021-09-01T00:00:00Z http://ir.lib.seu.ac.lk/handle/123456789/6616 Title: The smart hybrid chamber for cinnamon drying and storing operations Authors: Tharaka, W. L. R.; Narmilan, A.; Ajmal Hinas, M. N.; Abdul Hameed, M. I. M. Abstract: Drying, cooling, and storing food is a challenging task in many food manufacturing industries. Measuring temperature and humidity using the Arduino tool and sensors, which helps balance the environmental factors to increase productivity in the agricultural sector. This product is significantly related to Cinnamon storing and drying because industries are facing several issues related to controlling the storage condition. Therefore, controlling humidity and temperature into the cinnamon storage room is very important to reduce the postharvest losses. The standard optimum humidity level of cinnamon storage is 60% - 70%, and the temperature level is 27oC - 30oC. This primary aim is to develop a smart hybrid drying chamber and make storing unit for Cinnamon. This product included monitoring indoor humidity levels, controlling temperature and humidity levels, and sending notifications across Bluetooth modules to a mobile application. Furthermore, this process mainly using an Arduino UNO microcontroller, DHT11 sensor, and Bluetooth module. The result of this project helped to bring about a qualitative and quantitative change in cinnamon export. All the system functions are controlled automatically, so it is more advantageous and more efficient for cinnamon industries. 2021-09-01T00:00:00Z http://ir.lib.seu.ac.lk/handle/123456789/6615 Title: Sustainable management of nematodes infestation of paddy cultivation in Sri Lanka Authors: Sarathchandra, S. R.; Jayananda, S. Y. R.; Jayaweera, M. P. H. K.; Hennayake, K. P. S. D.; Rajapaksha, R. M. C. Y.; Dissanayake, D. M. O. K. B.; Kumara, A. D. N. T. Abstract: The rice root-nematode Hirschmanniella oryzae, and rice root-knot nematode, Meloidogyne graminicola have emerged as a major threat to rice cultivation. Therefore, the management of nematodes is highly essential for reducing severe damages in rice cultivation. A pre-tested questionnaire survey was conducted in five selected districts. Farmers were selected from farmer communities in each site by using a simple random sampling method (n=150) and, evaluated the effectiveness of new molecules of nematicide and non-chemical management package against nematode in a field experiment. The treatments were Abamectin 0.5% GR with three different dosages, poultry manure, paddy husk, and untreated control with three replicates. Area of 50 m2 each plot arranged in a Randomized Complete Block Design. The number of nematodes in soil, root-knot percentage, and yield data were recorded. The survey revealed that farmers in Mahaweli Systems B and C suffered from yield loss due to nematode attacks. The experiment results indicated that Abamectin 0.5% GR is effective for managing nematodes irrespectively of the dosage. Moreover, the application of poultry manure and paddy husk reduced nematodes from21/20g soil to 6/20g. The pilot trial indicated that there was no significant difference among Abemactin and organic manure applied fields in both nematode count and final yield. Therefore, it can be suggested, the application of poultry manure and paddy husk is a cost-effective, environmentally friendly method for controlling nematodes in the rice field. However, further large scale adaptive trials are needed to confirm and develop the well-adapted, non-chemical package against nematodes in rice fields. 2021-09-01T00:00:00Z http://ir.lib.seu.ac.lk/handle/123456789/6614 Title: Product attribute extraction from C2C social media messages Authors: Rilfi, Mohamed Refai Mohamed Abstract: On social media, people could share information related to their desire to purchase, sell, or consume products or services, which serves as a marketplace for C2C e-Commerce. However, the message post by the social media users will not reach the potential buyer/seller out of your followers’ circle. Furthermore, due to the difficulties of interpreting the semantics of social media posts, extracting product attribution from them is also difficult. To fix these issues, our research proposes a framework for extracting product attributes from microblogging messages about product selling and buying in this paper. First, we use a hybrid approach that includes Knowledge Base (KB), rule-based, Conditional Random Field (CRF), and Logistic Regression to extract the semantics of messages using named entity recognition. The dataset was created using raw social media messages, product descriptions from ecommerce sites, and KB because there was no product attribute annotated training dataset. When applied to a real-world dataset, the proposed approach achieves high accuracy, with classification and CRF models achieving 95 and 82 percent accuracy, respectively. 2021-09-01T00:00:00Z