Extreme Learning Machine (ELM) is one of the artificial neural network method that introduced by Huang, this method has very fast learning capability. ELM is designed for balance data. Common problems in real-life is imbalanced data problem. So, for imbalanced data problem needs special treatment, because characteristics of the imbalanced data can decrease the accuracy of the data classification. The proposed method in this study is modified ELM to overcome the problems of imbalanced data by integrating the data selection process, which is called by Integrating the data selection and extreme learning machine (IDELM. Performances of learning method are evaluated using 13 imbalanced data from UCI Machine Learning Repository and Benchmark Data Sets for Highly Imbalanced Binary Classification (BDS). The validation includes comparison with some learning algorithms and the result showcases that average perform of our proposed learning method is compete and even outperform of some algorithm in some cases

—Corona virus is a virus capable of mutating very quickly and many other viruses that arise due to mutations of this virus. To find out the location of corona virus mutations of one type to another, DNA sequences can be aligned using the Needleman-Wunsch algorithm. Corona virus data was taken from Genbank National Center for Biotechnology Information from 1985-1992. The Needleman-Wunsch algorithm is a global alignment algorithm in which alignment is performed to all sequences with the complexity of O (mn) and is capable of producing optimal alignment. An important step in this reserach is the sequence alignment of two corona viruses using the Needleman-Wunsch algorithm. Second, identification of the location of mutations from the DNA of the virus. The result of this reserach is an alignment and the location of mutations of both sequences. The results of identification DNA mutation can be used to find out other viruses mutation corona virus as well as can be used in the field of health as a reference for the manufacture of drugs for corona virus mutation outcome.

Dengue Hemorrhagic Fever (DHF) is one of the major health problems in Indonesia. With increasing mobility and population density, weather changes, other epidemic factors, the number of dengue fever patients also increases. In order to optimize the prevention of DHF outbreaks, it is important to obtain predictions related to the risk level of DHF outbreak, because each region needs to be treated according to its risk level. The spread of DHF is closely related to weather conditions. Therefore in this study, we apply extreme learning machine (ELM) method to predict the risk of outbreak based on weather condition. We Develop ELM architecture with weather variables as input nodes and risk level of DHF outbreak as the target. We use binary sigmoid activation function and bipolar sigmoid with a number of hidden neurons between 5- 200 nodes. The results show that ELM can predict the level of risk of DHF with the best performance of ELM network using a binary sigmoid activation function with 50 hidden neurons.

Avian influenza subtype A/H9N2—which infects chickens, reducing egg production by up to 80%—may be transmissible to humans. In humans, this virus is very harmful since it attacks the respiratory system and reproductive tract, replicating in both. Previous attempts to find antiviral candidates capable of inhibiting influenza A/H9N2 transmission were unsuccessful. This study aims to better characterize A/H9N2 to facilitate the discovery of antiviral compounds capable of inhibiting its transmission. The Symmetry of this study is to apply several machine learning methods to perform virtual screening to identify H9N2 antivirus candidates. The parameters used to measure the machine learning model’s quality included accuracy, sensitivity, specificity, balanced accuracy, and receiver operating characteristic score. We found that the extreme gradient boosting method yielded better results in classifying compounds predicted to be suitable antiviral compounds than six other machine learning methods, including logistic regression, k-nearest neighbor analysis, support vector machine, multilayer perceptron, random forest, and gradient boosting. Using this algorithm, we identified 10 candidate synthetic compounds with the highest scores. These high scores predicted that the molecular fingerprint may involve strong bonding characteristics. Thus, we were able to find significant candidates for synthetic H9N2 antivirus compounds and identify the best machine learning method to perform virtual screenings.

In recent years efforts on reducing fuel consumption has become the greatest issue related to energy crisis and global warming. The reduction of fuel consumption can be obtained, if the ship propulsion could be operated in its best performance level. Generally this is done by an appropriate analysis of engine propeller matching (EPM). In this study an EPM based on neural-network method, or NN-EPM, is established to predict the best performance of main engines, leading at minimum fuel oil consumption. A trimaran patrol ship is selected as a case study. This patrol ship is equipped with two 2720 kW main engines each connected to a controllable pitch propeller (CPP) through a reduction gear. The input parameters are ship speed V and service margin SM, with the corresponding output parameters comprise of engine speed n_E, engine break horse power P_B, propeller pitch P/D, and the fuel consumption FC. An NN-EPM 2-20-15-4 configuration has been constructed out of 100 training data and then validated by 30 testing data. The maximum relative error between results from NN-EPM and EPM analysis is 2.1%, that is in term of the fuel consumption. For other parameters the errors are well below 1.0%. These facts indicate that the use of NN-EPM to predict the main engines's performance for trimaran patrol ship is satisfactory.