Volume 03 Issue 02

Convolution neural network based priority prediction approach for GITHUB issues

2021-12-31T00:00:00Z

Convolution neural network based priority prediction approach for GITHUB issues Madubashini, D. A. P.; Wijesiriwardana, C. A bug report is an important document that outlines software problems that result in unexpected errors or wrong outcomes. In large software projects, a high number of bugs are reported daily, which needs to be systematically analyzed. Predicting the priority level of reported bugs, assigning an appropriate developer, finding duplicate issues, and predicting bug resolving time are some of the critical tasks in the bug analysis process. Due to the inherent complexity of the bug analyzing process, manual bug investigation requires a significant amount of time, resources, and effort. Therefore, the need to establish automated or semi-automated approaches for assessing bug reports is extensively discussed in the literature. This research presents a novel approach to prioritize the bug reports by exploiting a Convolutional Neural Network-based approach. Furthermore, this research investigates the impact of both textual and categorical features of bug reports in improving the accuracy of priority prediction. The experiments were conducted by extracting the bug reports available in three GitHub repositories. The evaluation results confirm that the use of categorical features does not have an impact on the accuracy of the priority prediction of bug reports. Furthermore, it was observed that better prediction accuracies are shown for the datasets extracted from Bugzilla than GitHub repository

Quality evaluation of whipping cream incorporated with coconut cream as an alternative for dairy cream

2021-12-31T00:00:00Z

Quality evaluation of whipping cream incorporated with coconut cream as an alternative for dairy cream Kavindi, R. P. C.; Jemziya, M. B. F.; Gunathilaka, R. M. S.; Rifath, M. R. A. Whipping cream is widely used in food services and catering. Due to the high and exorbitant expense of milk cream, the replacement of coconut cream reduces the cost. This study aimed to develop a coconut cream-incorporated whipping cream and to determine the quality of composites. The whipping cream was prepared using coconut cream and dairy cream with different proportions as 100 % dairy cream, 100 % coconut cream, 30 % coconut cream + 70 % dairy cream, 10 % coconut cream + 90 % dairy cream. The whipping properties such as whipping time and % overrun, physicochemical properties such as moisture, fat, total solid, solid non-fat and ash content and sensory evaluation was conducted using the nine-point hedonic scale to determine colour, flavour, texture, taste, odour, and overall acceptability. There were significant differences observed in the whipping properties and the physiochemical properties among the treatments. Of which, 30 % coconut cream + 70 % dairy cream sample had 96s whipping time, 108 % overrun, 47.05 % moisture, 52.45 % total solids, 31.40 % solid non-fat and 21.05 % fat content. Whereas, it scored the overall higher values in terms of sensory profile. Therefore, it was selected as the best formulation based on the quality properties including whipping properties, physicochemical properties and sensorial properties. Eventually, the blending of coconut milk and dairy milk improved the whipping properties, physicochemical properties, and sensory properties. Further, coconut cream could be used as a replacer for dairy cream in the whipping cream at a certain level.

Comparative study of physical egg quality characteristics of naked neck and bovans chicken in diverse ages in coastal areas of Ampara district

2021-12-31T00:00:00Z

Comparative study of physical egg quality characteristics of naked neck and bovans chicken in diverse ages in coastal areas of Ampara district Mohamed Thariq, M. G.; Silva, P. M. R.; Rikasa, A. M. The chicken egg is a high-quality protein food widely consumed all over the world. Consumer acceptance is a determining factor of egg quality with respect to cleanliness, freshness, egg weight, shell quality, yolk index, albumen index, Haugh unit and chemical composition. The present study investigated the physical quality characteristics of eggs of Naked neck (village) and Bovans (commercial) chicken breeds in coastal areas of Ampara district. A total of 60 eggs, 30 from each breed were purchased for analysis. The eggs were stored at room temperature during analysis. The egg weight, egg length, egg width, shape index, shell weight, shell thickness, albumen pH, albumen height, Haugh unit, yolk height, yolk length, yolk width, yolk index and yolk color were determined. The study revealed that the egg weight, shell width, shell weight, shell thickness and yolk color were significantly different (p<0.01) between the eggs of Naked neck and Bovans breeds whereas egg length, shape index, albumin pH, albumen height, Haugh unit, yolk height, yolk length, yolk width and yolk index were not significantly different (p<0.05). The mean egg weight of Naked neck chicken was lower than Bovans chicken’s eggs. The shell strength of Bovans chicken eggs is better than Naked neck chicken eggs. From the findings of the study, it is concluded that several physical external quality characteristics investigated are found to be at a higher level in Bovans chicken eggs than in Naked neck chicken eggs.

Quantitative models for prediction of palm olein adulteration in coconut testa oil

2021-12-31T00:00:00Z

Quantitative models for prediction of palm olein adulteration in coconut testa oil Gunarathne, K. M. R. U.; Marikkar, J. M. N.; Yalegama, C. This study was carried out to produce quantitative models for prediction of palm olein (PO) adulterations in coconut testa oil (CTO) by using fatty acid compositional analysis and differential scanning calorimetric (DSC) analysis. Samples of authentic CTO were prepared using mature coconuts collected out of three local cultivars while a pure sample of PO was obtained from a reliable supplier. In this experiment, samples of CTO were blended with PO in the range of 20 to 80% (w/w) and subjected to fatty acid and thermal analysis using the relevant instruments. Fatty acid data and DSC data of thermal transitions namely, peak temperature, peak area, peak onset and peak endset temperatures were employed to perform statistical analysis. Results showed that all fatty acids were suitable as parameters to develop quantitative models for prediction of adulteration in CTO. The highest positive correlation was displayed by linoleic acid (+0.977; p<0.0001) followed by oleic (+0.973; p<0.0001), palmitic (+0.972; p<0.0001) and stearic (+0.959; p<0.0001) acids. Out of all, the two models formed using palmitic and oleic acids were the best for prediction. According to DSC analysis, the highest correlations were found for peak maxima (-0.965; p<0.0001) and peak area (-0.951; p<0.0001). Out of these two, the model formed using peak maxima was the best for prediction.