<p>Streptomyces hygroscopicus (S.hygroscopicus) is a Gram-positive soil bacterium that can produce secondary metabolites from fermentation that have a therapeutic effect. The fermented S. hygrocospicus metabolites that are still in the form of crude extracts are difficult to develop as drug preparations because the active compounds are not yet known, so it will be challenging to determine the dosage of drugs that have a therapeutic effect. Therefore, it is necessary to carry out exploratory research to narrow down the secondary metabolite profile from the fermentation of S. hygroscopicus, using extraction and fractionation methods, which are then identified by Thin-Layer Chromatography (TLC) using a combination of solvents. This study used the extraction method with a separating funnel. The fractionation was carried out using the BUCHI (Sepacore®) Flash Chromatography and Reveleris® PREP Purification System column chromatography gradually using ethyl acetate and n-hexana.  47 and 60 of the fractionation results were taken as samples, that further were profiled using TLC and given the appearance of 10% KOH stains and p-Anisaldehyde - sulfuric acid, so that various classes of compounds with different Rf values were obtained, namely Monoterpenes, Triterpenes, Steroids, Saponins, Coumarin, Scopoletin, and Alkaloids.</p>

<span id="docs-internal-guid-ebf19048-7fff-9350-093e-7f1e8df23393"><span>Acute sinusitis is the most common form of sinusitis, and it causes swelling and inflammation within the nose. The main thing that can causes sinusitis is probably due to viruses, and also can be caused by other factors, namely bacteria, fungi, irritation, dust, and allergens. In this research, the CT scan data attributes will be used for classification and grey wolf optimization-support vector machine (GWO-SVM) will be the machine learning technique used, where the GWO technique will be used to tuned the parameters in SVM. The performance of methods was analyzed using the python programming language with different percentages of training data, which started from 10% to 90%. The GWO-SVM method proposed provides better accuracy than using SVM without GWO.</span></span>

Cerebral infarction is focal brain necrosis due to complete and prolonged ischemia that affects all tissue elements, neurons, glia, and vessels. Stroke infarction or known as cerebral infarction is a condition of damage in the brain due to insufficient oxygen supply, due to obstruction of blood flow to the area. Research shows stroke infarction does not only occur in the elderly, but occurs at a young age of around 15-55 years, especially with certain risk factors, such as diabetes, hypertension, heart disease, smoking, and long-term alcohol consumption. In diagnosing the presence of cerebral infarction in the brain, machine learning is used because it is not enough just to use a CT scan to diagnose. Therefore, it requires timely detection and more accurate methods of classification. This study aims to use Support Vector Machine (SVM) as preprocessing and K-Nearest Neighbors (KNN) algorithm to classify Infarction Cerebral. In this study, discusses the application of SVM to deal with class imbalances. The first strategy is to balance data using SVM as a preprocessor and the actual target value of the training data is then replaced by trained SVM predictions. Then, the modified training data is used to classify with K-NN method. We use data CT scan result from a Department of Radiology at Dr. Cipto Mangunkusumo Hospital (RSCM). This accuracy in this paper shows around 69,85 %.

A cerebral infarct is a circumscribed focus or area of brain tissue that dies as a result of localized hypoxia or ischemia due to cessation of blood flow. To diagnose the presence of cerebral infarction, it needs a CT scan result from the patient. But, in this study not only CT scan result will be used, machine learning also will be proposed to diagnosing cerebral infarction. Machine learning can be used to detect and classify of infarcts in the brain using features and label that obtained from the results of the CT scan. In this study, the machine learning method that will be used is K-Means and K-Means based on kernel or kernel K-Means. Kernel K-Means is the application of K-Means that modified by changing the inner product with kernel function. The CT scan result data used in this study was obtained from the Department of Radiology at Dr. Cipto Mangunkusumo Hospital (RSCM). The best result reached with kernel K-Means, it performed with different percentage of training data, started with 50%, 55%, until 95% data training. The average accuracy score of the kernel K-Means method attained an accuracy rate of 95.28%.