A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Moreover, in the classification of multiple classes with neural network, a training pattern is treated as a positive pattern in one output node and negative in all the remaining output nodes. In this paper, the weights of a training pattern in the loss function are designed based not only on the number of the training patterns in the class but also on the different nodes where one of them treats this training pattern as positive and the others treat it as negative. We propose a combined approach of weights calculation algorithm for deep network training and the training optimization from the state-of-the-art deep network architecture for thorax diseases classification problem. Experimental results on the Chest X-Ray image dataset demonstrate that this new weighting scheme improves classification performances, also the training optimization from the EfficientNet improves the performance furthermore. We compare the aggregate method with several performances from the previous study of thorax diseases classifications to provide the fair comparisons against the proposed method.

Learning applied in Indonesia from elementary school to undergraduate level generally uses face-to-face or direct learning methods. However, after the Covid-19 disease outbreak, all methods change to online learning methods at all levels and cultures. This affects all aspects of learning such as comfort, understanding and learning outcomes. To find out the difference in the results using face-to-face methods and online methods, a study was carried out on classifying learning media users from elementary school to university level using the k-means method. This study aimed to determine the differences in learning outcomes between the semester before the Covid-19 pandemic and the semester during the Covid-19 pandemic which applies online learning. The results of grouping data on online learning media users showed that all levels of education were considered sufficiently ready to implement online learning. As well as cultural differences in Indonesia have not had an impact on the commitment of schools to implement online learning during the Covid-19 disease outbreak.

The purpose of this study aims to get the best combination of palm oil midrib and coconut midrib in making charcoal briquettes. The study was conducted experimentally using a complete randomized design method consisting of 5 treatments and 3 replications. The treatments in this study were the ratio of palm oil midrib and coconut midrib charcoal as follows: KSK1 (100:0), KSK2 (75:25), KSK3 (50:50), KSK4 (25:75) and KSK5 (0:100). The parameters observed were density, water content, ash content, vapour content, bound carbon content and heating value. The result of palm oil midrib and coconut midrib shells had a significant effect on density, water content, ash content, vapour content, bound carbon content and heating value. Based on the results of the analysis, the best treatment in this study were KSK4 of palm oil midrib and coconut midrib (25:75) with a density of 0,58 g/cm3, water content 5,82%, ash content 5,87%, evaporating content 15,01%, bound carbon content 79,12%, and heating value content 6596,65 cal/g.

No abstract

No abstract