Search

Jamu is an herbal medicine commonly used before the advent of modern medicine. Generally, the herbal formula is obtained empirically and passed down from generation to generation. However, the healing process with herbs is also influenced by such as myths and local customs. This influence causes differences in the use of herbal ingredients to cure the same disease. The result is a collection of herbal recipes that overlap each other without any supporting evidence of its validity. Protein-protein interaction (PPI) is a biological process that is influenced by drugs in the healing process. Therefore, PPI due to the consumption of herbs can be used as evidence of the effectiveness of herbal medicine. PPI analysis needs to be done to study how proteins interact with other proteins. PPI analysis with an experimental method (wet lab) cannot be carried out on extensive data and only covers a portion of protein interaction networks. Therefore, a computational approach needs to be done. In previous studies, predictions of PPIs were proven to be carried out using only protein sequence information. The advantage of using this protein sequence information is that this method is more universal. Information that can be obtained from protein sequences includes Discrete Cosine Transform, Multi-scale Local Descriptor, Autocovariance, and Conjoint Triad. The study with the sequence information has been done using different machine learning approaches, such as Support Vector Machines, Random Forest, and Probabilistic Neural Networks. A deep learning approach has also been done with Stacked-Autoencoder, which tried to construct a hidden structure of protein sequences. Previously, deep learning has also been proven to be able to handle raw and complex data on a large scale and learn the useful and abstract features of perceptual problems such as image recognition and voice. The method proposed in this study is deep neural networks that were trained using stacked-autoencoder and stacked-randomized autoencoder. The extracted features used are conjoint-triad. This study compares both methods which have different characteristics in the construction of layers in deep neural networks. We conducted experiments with k-Fold cross-validation which became the gold standard for most predictive model testing. Our experiments with 5 cross-validations and 3 hidden layers gave an average validation accuracy of 0.89 ± 0.02 for the SAE method and 0.51 ± 0.003 for the ML-ELM. [ABSTRACT FROM AUTHOR]

A kinetic test, namely Humidity Column Test (HCT) was conducted in the laboratory to predict the mine drainage quality of two samples from a coal mine in Kalimantan, Indonesia. Furthermore, the study calculated the weathering rate of these samples per cycle and identified the parameters controlling the weathering process. The samples came from fresh rock of the active pit (PE) and disposal area (Q10). A static test was conducted to these samples and showed the classification results of the samples. HCT used uniform particle size distribution and aimed to interpret the kinetics of the acid generation. The results of 7 cycles (56 days) experiments are presented here. Based on the kinetic test, PE was classified as PAF high capacity and Q10 was classified as PAF intermediate capacity. The intensity of weathering rate was indicated by TDS (Total Dissolved Soil). It was in line with the pH paste results: the smaller paste pH, the faster the weathering rate. PE tended to weather faster than Q10. [ABSTRACT FROM AUTHOR]

Land conversion in the Sausu Watershed, Sulawesi, Indonesia has been started massively since 1990. During this period there have been changes in land cover from forest areas to more than 5,000 hectares of plantation land. The land conversion in the middle and upper watersheds is predicted to have triggered major floods which have resulted in large losses, especially in the downstream area as residential and agricultural land with an exposure area of more than 2,000 hectares. The flood in 1996 also has caused the collapse of the Upper Sausu Weir as a supplier of irrigation water for more than 7,000 hectares on the right and left sides of the river channel. This study was conducted to analyze the effect of land conversion in the watershed on increasing the flood peak using the ITS-2 Synthetic Unit Hydrograph Model, one of the flood peak prediction models developed at the Institut Teknologi Sepuluh Nopember in 2017. The research was preceded by data collection, especially rainfall data (daily and hourly), flow data and area conversion of forest land. Daily rainfall data were obtained from Sausu Rainfall Station with a range of 2000-2018, and hourly rainfall and discharge data were obtained from Nippon Koei Co Ltd. with a short range in 2002. The main research was carried out in two stages, namely, calibration to determine the optimal parameters of the ITS-2 Model and the application of the model for flood peak analysis. Rainfall as the input of the model can be defined as design rainfall with 50-year return periods, which are previously transformed to net rainfall. The losses due to evapotranspiration and infiltration were analyzed using Curve Number Method based on cover type and hydrologic condition of the watershed. The results of the analysis have indicated that land conversion in the watershed has increased the potential of peak flow to 16.5% when evaluated on these return period of flows. The peak of this flood does not seem to increase significantly compared to the great floods of the past. However, it must be understood that flooding can occur not only due to changes in land cover but can also occur due to various other factors such as changes in the characteristics of rainfall which leads to extreme rainfall with high intensity and long duration. [ABSTRACT FROM AUTHOR]