Search

Sentiment analysis is a data text analysis that classifies data into positive and negative sentiments. This study aims to obtain the results of sentiment classification related to Merdeka Belajar Kampus Merdeka policy on Twitter using support vector machine algorithm with Word2Vec feature extraction. Support Vector Machine is a classification algorithm that separates data classes using the optimum hyperplane. Text data used in sentiment analysis must change its numerical form by performing feature extraction. In this study, the feature extraction used is Word2Vec which represents words in vector form. Data in this study are tweets with the keyword "Kampus Merdeka" uploaded on Twitter as many as 10000 tweets. After preprocessing text data, data used to analyze sentiment was 1579 tweets. Sentiment classification resulted in classification model accuracy 89.87%, precision 91.20%, recall 84.44% and F-Measure 87.68%. Classification sentiment using support vector machine with Word2Vec feature extraction in this study produces a good model.

Twitter is one of the popular social media used to get news quickly and briefly. After the outbreak of the COVID-19 virus and the government's policy to vaccinate against COVID-19 in Indonesia, more and more public opinion has been expressed through tweets. This makes the topic of COVID-19 vaccination interesting for sentiment analysis. Through sentiment analysis, information in the form of text data can be extracted to classify information related to positive or negative opinions. In this study, the classification of public opinion on COVID-19 vaccination was carried out using the supporting vector machine method without and with lexicon-based features. The manual labeling data used were 2981 tweets. The results of the classification of public opinion on COVID-19 vaccination in Indonesia with a supporting vector machine without the lexicon feature obtained accuracy, g-mean and AUC of 83%, 50% and 61.35%, respectively. Meanwhile, with lexicon-based features, the performance of the supporting vector machine method for classifying public opinion on COVID-19 vaccination in Indonesia obtained accuracy, g-mean and AUC of 90%, 86.63% and 87%, respectively. Based on these results, the performance of the supporting vector machine method with lexicon-based features provides better results for the performance of classifying of public opinion on COVID-19 vaccination compared to supporting vector machines without lexicon-based features.

The accuracy of the data class is very important in classification with a machine learning approach. The more accurate the existing data sets and classes, the better the output generated by machine learning. In fact, classification can experience imbalance class data in which each class does not have the same portion of the data set it has. The existence of data imbalance will affect the classification accuracy. One of the easiest ways to correct imbalanced data classes is to balance it. This study aims to explore the problem of data class imbalance in the medium case dataset and to address the imbalance of data classes as well. The Synthetic Minority Over-Sampling Technique (SMOTE) method is used to overcome the problem of class imbalance in obesity status in Indonesia 2013 Basic Health Research (RISKESDAS). The results show that the number of obese class (13.9%) and non-obese class (84.6%). This means that there is an imbalance in the data class with moderate criteria. Moreover, SMOTE with over-sampling 600% can improve the level of minor classes (obesity). As consequence, the classes of obesity status balanced. Therefore, SMOTE technique was better compared to without SMOTE in exploring the obesity status of Indonesia RISKESDAS 2013.

In Indonesia malaria is found to be widespread in all islands with varying degrees and severity of infection. Based on the Annual of Parasite Incidence (API) in Eastern Indonesia, Malaria is a disease that has a high incidence rate. The three provinces with the highest APIs are Papua (42.64%), West Papua (38.44%) and East Nusa Tenggara (16.37%). Spatial aspects are considered important to be studied because the spread of disease through mosquitoes is strongly influenced by fluctuating climate. The purpose of this study is to determine the potential factors that influence the incidence of Malaria disease in the province of Papua in 2013 by looking at aspects that are the focus of attention in spatial epidemiology. The methods used in analyzing the area are Simultaneous Autoregressive (SAR) and Conditional Autoregressive (CAR) models with a spatial weighting matrix up to second order. The result shows the average monthly wind velocity, average monthly rainfall, and malaria treatment with government program drugs by getting ACT drugs are substantial factors in determining the incidence number of Malaria in Papua based on the lowest AIC value for the second-order of CAR model. While the SAR model, in this case, has no spatial influence. By knowing the potential factors that influence the incidence of malaria, the Papua Province through the Health Office can take more effective preventive measures to reduce the number of malaria incidents.

Diabetes mellitus (DM) is one of the chronic and deadly diseases that are widely observed in various countries today. This disease continues and is increasing to a very alarming stage. This study aims to identify and see the relationship between factors that influence DM disease. The method used in this research is C4.5 algorithm which is one of the algorithms used to make predictive classifications. Classification is one of the processes in data mining that aims to find patterns in relatively large data that use the representations in the form of decision trees. This method is applied to data from medical records of patients with DM in 2014-2018 taken from the Hasanuddin University Teaching Hospital. The results obtained indicate that there are four factors that influence the prediction of a patient's DM status namely; Fasting Blood Glucose (GDP), LDL Cholesterol, Triglycerides, and Body Weight.

Obesity has become a rising global health problem affecting adults’ quality of life. The objective of this study was to describe the prevalence of obesity in Indonesian adults based on the cluster of islands. The study was also aimed to identify the risk factors of obesity in each island cluster. This study analysed secondary data of Indonesian Basic Health Research 2018. Our data for analysis comprised 688,638 adults (>=15 years) randomly selected using proportionate to population size throughout Indonesia. We included 20 variables for sociodemographic and obesity-related risk factors for analysis. Obese status was defined using Body Mass Index (BMI) >= 27.5 kg/m2. Our current study defined seven major islands cluster as the unit analysis consisting of 34 provinces in Indonesia. Descriptive analysis was conducted to determine the characteristics of the population and to calculate the prevalence of obesity within provinces in each of the island’s clusters. Multivariate logistic regression analyses to calculate odds ratios (ORs) was performed using R version 3.6.3. The study results showed that all island clusters had at least one province with an obesity prevalence of more than 20%. Six out of twenty variables, comprising four diet factors (consumption of sweet food, high-salt food, meat food, and carbonated drinks) and two other factors (mental health disorders and smoking behaviour), varied across the island clusters. In conclusion, there was a variation of obesity prevalence of the provinces within and between island clusters. Variation of risk factors raised in each cluster island suggested the government rethink and reframe the intervention to address obesity.

Wave energy resource assessment and trends around Indonesian’s ocean has been carried out by means of analyzing satellite observations. Wave energy flux or wave power can be approximated using parameterized sea states derived from satellite data. Unfortunately, only some surface parameters can be measured from remote sensing satellites, for example for ocean surface waves: significant wave height. Others, like peak wave period and energy period are not available, but can instead be estimated using empirical models. The results have been assessed by meteorological season. The assessment shows clearly where and when the wave power resource is promising around Indonesian’s ocean. The most striking result was found from June to August, in which about 30–40 kW/m (the 90th percentile: 40–60 kW/m, the 99th percentile: 50–70 kW/m) wave power energy on average has been found around south of the Java Island. The significant trends of wave energy at the 95% level have also been studied and it is found that the trends only occurred for the extreme cases, which is the 99th percentile (i.e., highest 1%). Wave power energy could increase up to 150 W/m per year. The significant wave heights and wave power have been compared with the results obtained from global wave model hindcast carried out by wave model WAVEWATCH III. The comparisons indicated excellent agreements.

Obesity is strongly associated with multiple risk factors. It is significantly contributing to an increased risk of chronic disease morbidity and mortality worldwide. There are various challenges to better understand the association between risk factors and the occurrence of obesity. The traditional regression approach limits analysis to a small number of predictors and imposes assumptions of independence and linearity. Machine Learning (ML) methods are an alternative that provide information with a unique approach to the application stage of data analysis on obesity. This study aims to assess the ability of ML methods, namely Logistic Regression, Classification and Regression Trees (CART), and Naïve Bayes to identify the presence of obesity using publicly available health data, using a novel approach with sophisticated ML methods to predict obesity as an attempt to go beyond traditional prediction models, and to compare the performance of three different methods. Meanwhile, the main objective of this study is to establish a set of risk factors for obesity in adults among the available study variables. Furthermore, we address data imbalance using Synthetic Minority Oversampling Technique (SMOTE) to predict obesity status based on risk factors available in the dataset. This study indicates that the Logistic Regression method shows the highest performance. Nevertheless, kappa coefficients show only moderate concordance between predicted and measured obesity. Location, marital status, age groups, education, sweet drinks, fatty/oily foods, grilled foods, preserved foods, seasoning powders, soft/carbonated drinks, alcoholic drinks, mental emotional disorders, diagnosed hypertension, physical activity, smoking, and fruit and vegetables consumptions are significant in predicting obesity status in adults. Identifying these risk factors could inform health authorities in designing or modifying existing policies for better controlling chronic diseases especially in relation to risk factors associated with obesity. Moreover, applying ML methods on publicly available health data, such as Indonesian Basic Health Research (RISKESDAS) is a promising strategy to fill the gap for a more robust understanding of the associations of multiple risk factors in predicting health outcomes.

Objective To understand the spatial pattern of dengue fever (DF) patients’ survival and investigated factors influencing DF patients’ survival. Method A Bayesian spatial survival method via a conditional autoregressive approach was used to analyze the factors that influence DF patients’ survival in 14 sub-districts from January 2015 to May 2017 in Makassar city, Indonesia. Bayesian spatial and a non-spatial model were compared by using deviance information criterion. Results The spatial model was more suitable than a non-spatial model. Under the Bayesian spatial model, there was a substantive relationship between age, grade and DF patients’ survival time. Conclusions The relative risk map and related factors of DF patients’ survival can indicate the health policy makers to give special attention to the high risk areas in order to faster and more targeted treatment.

Daring mathematics study leaves pupils with troubles and anxiety after more than a year of daring learning. Furthermore, students often struggle to understand instructional materials that need graphic interpretation when learning mathematics. This activity aims to improve the competence of mathematics teachers with skills using the iSpring and GeoGebra so that they can create creative and effective learning media so that their virtual mathematics learning becomes more interesting and understandable for students. This activity is conducted daring via Zoom and live on YouTube, as well as offline meetings that are carried out with due observance of health protocols. Lectures, demonstrations on the use of iSpring and GeoGebra, as well as monitoring and evaluation are methods used in daring and offline activities. The target audience for this community service is Middle School Mathematics teachers in Pattalassang District. The results of the training showed an increase in the understanding and skills of mathematics teachers in utilizing iSpring and GeoGebra multimedia. This improvement in IT skills can contribute to increasing creativity and effectiveness in learning mathematics in the classroom.

Type 2 Diabetes Mellitus is a group of disorders with characteristics such as insulin resistance, impaired insulin secretion, and increased glucose production, which has patients reaching 90% - 95% of the overall population of people with diabetes mellitus. There at most 70% of Indonesians are unaware attacked by diabetes. Therefore, an early detection has an important role and the utilization of microarray technology can cope this problem. One of the challenges for microarray applications is to select an appropriate number of the most significant genes for data analysis. Besides that, it is hard to accomplish a satisfactory classification results by Support Vector Machine (SVM) due to the dimensionality and the over-fitting problems. For this reason, it is desirable to select informative genes firstly in order to improve classification accuracy of SVM classifier. In this study, we use the Information Gain in order to determine informative features of data to get better classification performances and then the SVM is applied to the selected features. Based on the result, the informative genes were selected from 25,770 to 309 genes. SVM can predict sample with accuracy 100% and area under curve 100%. There is a probe which is a gene that has various functions, including regulating neurotransmitter releases, heart rate, insulin secretion, neuronal excitability, epithelial electrolyte transport, smooth muscle contraction, and cell volume.

Analysis of the relative risk of the spread of dengue fever (DF) in Makassar city, Indonesia, needs to be done to see the which areas are at high risk of DF. Bayesian Autoregressive Conditional (CAR) is used in the mapping model of this disease. This model is Able to model of relative risk by taking into account the smoothing of that relative risk and entering spatial information to reduce the error of the estimated parameters in order the reliable relative risk models is Obtained. In this study, the relative risk value of the spread of DF was Analyzed using the localized Bayesian models CAR. Under this model the geographical mapping of DF in Makassar can be identified for each sub-district and shows that Makassar is still very vulnerable to DF.

One of the health problems in Makassar city is dengue fever (DF) disease. To find out areas in Makassar that are at high risk of spreading DF, a relative risk analysis can be done. Bayesian Conditional Autoregressive (CAR) is a model used in disease mapping by taking into account the smoothing of the estimated relative risk and using spatial information to obtain a better estimate of relative risk. The Leroux model is a prior used in the CAR model for estimating the relative risk of DF in Makassar city. The relative risk estimation is used for geographic mapping of DF. In this model random and spatial variables are used. The results of this study indicate that DF medium relative risk occurred in some sub-districts of Makassar city. It indicates that the population in these areas susceptible and more likely to be infected with DF disease. This gives a clue so the Health Department of Makassar city can provide more intensive treatment to medium relative risk sub-districts so that the spread of DF disease in Makassar can be overcome.

Microarray technology has the ability to measure the level expression of thousand genes by single experiment and it can be used by biologist to study about the effect of treatments, disease and developmental stages on their expressions. Microarray based on gene expression profiling can be used to observing the response of expression genes to pathogens and identify which expressions genes are changed by comparing the expression in infected to that uninfected cells or tissue. Type 2 diabetes mellitus is a metabolic disorder that causes an increase in blood sugar due to decreased insulin secretion by pancreatic beta cells and insulin disorder (insulin resistance). The number of incidences of diabetes mellitus in Indonesia reached 10 million and 53% from the patients do not realized that they are infected and 90% case of diabetes from whole world is type 2 of diabetes. Therefore, in this paper, we identify probable biomarker of type 2 diabetes using microarray based on gene expression data. But the risk of using microarray data is the large dimension of data so have to find a way how to solve that problem to get a good prediction result. In this paper will use recursive feature extraction for predicting biomarkers of diabetes mellitus type 2 from microarray gene expression data.

Bayesian Conditional Autoregressive (CAR) is used in disease mapping because it is able to model relative risks by taking into account the smoothing of the estimated relative risk and entering spatial information to reduce the errors of the estimated relative risk parameters so that a more reliable relative risk model is obtained. In this study, the relative risk value of the spread of dengue fever will be calculated using Bayesian CAR with the localised model. These results were obtained using the OpenBUGS program and are illustrated in the 2016 dengue fever case data. Based on the model, mapping of dengue fever in Makassar can be identified in each district and shows that Makassar City is still very vulnerable to dengue fever.

The involvement of teachers in Bone Regency in using information and communication technology (ICT) to prepare teaching materials is very little or even never said, even though computer facilities and infrastructure are available in the computing lab. This activity aims to provide knowledge to Mathematics teachers about online learning Google Classroom and Geogebra. The use of Google Classroom will make learning more effective for teachers and students because learning is no longer limited by space and time, student can explore learning resources easily and utilize information technology properly. Likewise, Geogebra training is expected to overcome the difficulties of teachers in visualizing concept charts in mathematics dynamically. The target audience for community service is mathematics teachers who are members of the Mathematics MGMP in Bone Regency.

Breast cancer (carsinoma mammae) is one type of cancer that occurs due to abnormal breast cell growth. Some of the factors that are thought to trigger breast cancer include the unhealthy lifestyles. The existence of these factors indicates that there is a correlation between breast cancer and patient survival. One of method for analyzing survival data is Cox proportional hazard. Cox proportional hazard model implies that each covariate is proportional. But in reality, there are often cases where there is a disproportionate covariate, in the sense that there is a relationship with the time, called time dependent covariate. In this case an extended of the Cox proportional hazard model needs to be done. Therefore, the aim of this paper to determine the relationship between the breast cancer patients’ survival time and the factors that influence it using extended Cox model with Bayesian approach. This methodology is applied to breast cancer survival data from Hasanuddin University hospital in Makassar, Indonesia, for the period 2005-2018. The result shows the factors that substantially affect the breast cancer patients’ survival time are marital status, histology, and leukocyte levels.

Diabetes mellitus (DM) is one of the chronic and deadly diseases that are widely observed in various countries today. This disease continues and is increasing to a very alarming stage. Indonesia ranks fourth in the world with the highest DM after the United States, India and China. The method used in this study is data collection, variable selection, classification methods, validation and evaluation and decision making. The algorithm used in this study is C4.5 Algorithm and Naive Bayesian Method using a dataset obtained from the results of Hasanuddin University hospital medical records. The results of calculations that have been done obtained accuracy on the C4.5 algorithm of 100% and on the Bayesian naive method obtained at 90%. From these results it can be concluded that to diagnose DM disease it is recommended to use the C4.5 Algorithm .

To present the geographical map of Dengue fever (DF) in Makassar city, Indonesia, we used the registered DF data to compute the relative risk (RR) of DF in different areas of Makassar city, Indonesia, for a five-year period (from 2012 to 2016). This paper aim to identify the the spatial distribution of DF occurrence to provide the map of risk area in Makassar City through the geographical map. To estimate RR for DF in Makassar City, Indonesia, the Besag York Mollie (BYM) model was proposed. The Bayesian estimates of DF relative risk were utilized for geographical mapping of DF. The results of the present study reveals that DF is still a serious health problem in Makassar city, Indonesia. The distribution of high and low risk areas of DF occurrences for all sub-districts in Makassar City can be identified in the risk geographical map to allow the better allocation and risk assessment.

A control chart is one of the primary techniques of statistical quality control. Exponentially Weighted Moving Average (EWMA) control chart is one of the control charts used to detect a small shift in the mean process. In the quality control process, the control chart is often constructed by ignoring parameter uncertainty. This can affect the long-term performance of the control chart in a controlled or out-of-control state, so parameter estimation is necessary. The parameter estimation method used in this paper is the Bayesian approach. The Bayesian approach is used to develop an EWMA control chart in monitoring a process. The performance of the EWMA control chart with the Bayesian approach has been evaluated using Average Run Length (ARL). Based on the comparison of the ARL value from the EWMA control chart with the Bayesian approach and the Classical EWMA control chart, it shows that the EWMA control chart with the Bayesian approach is more sensitive in detecting the shift in the mean process.

In many fields of applied studies, there has been increasing interest in developing and implementing Bayesian statistical methods for modelling and analysing the time-to-event data. Modelling the time-to-event data can be done by using the survival methods. In the survival data, we can find a set of complete records, in which the event and the survival time is known; and a set of censored records, in which the event was known to have occurred in an interval, but the survival time is unknown exactly. The time of an event frequently depends on the location; calls as spatial survival. In this paper, we performed a simulation study to estimate the spatial survival model parameters. The study was carried out with two different simulated datasets with right censored, which is, simulated assuming an exponential baseline hazard and a Weibull baseline hazard. The parametric proportional hazards model in which spatially correlated frailties with a log-Gaussian is the specific type of spatial model which is used. Th...

This papes discusses the theory and application of statistical methods for describing and analyzing survival times of the renal dialysis patients : a) from the first diagnosis until the time of death, and b) on each mode of given treatment. The paper also tries to predict the variables significantly effecting the survival time of renal dialysis patients. The paper makes use of and focuses on the data sets containing patient hospital records, patients’ identity and hospital code centre. To meet the desired aims, the paper uses two prominent methods of survival analysis including the Kaplan-Meier and Cox Proportional Hazard model. The result shows that survival time on the first treatment depends on mode of treatment and it quite low approximately 18 days for median time on hospital outpatient CAPD. Similarly, survival time on the second treatment is quite low about 24 days for the median time on hospital outpatient CAPD. It was also indicated that the survival time of renal dialysis patient depends on the number of treatments, the number of treatment changes, place of treatment, age and the first treatment

A boundary element method (BEM) is obtained for solving a boundary value problem of homogeneous anisotropic media governed by diffusion-convection equation. The application of the BEM is shown for two particular pollutant transport problems of Tello river and Unhas lake in Makassar Indonesia. For the two particular problems a variety of the coefficients of diffusion and the velocity components are taken. The results show that the solutions vary as the parameters change. And this suggests that one has to be careful in measuring or determining the values of the parameters.

Piecewise exponential models provide a very flexible framework for modelling univariate survival data. It can be used to estimate the effects of different covariates which are influenced by the survival data. Although in a strict sense it is a parametric model, a piecewise exponential hazard can approximate any shape of a parametric baseline hazard. In the parametric baseline hazard, the hazard function for each individual may depend on a set of risk factors or explanatory variables. However, it usually does not explain all such variables which are known or measurable, and these variables become interesting to be considered. This unknown and unobservable risk factor of the hazard function is often termed as the individual’s heterogeneity or frailty. This paper analyses the effects of unobserved population heterogeneity in patients’ survival times. The issue of model choice through variable selection is also considered. A sensitivity analysis is conducted to assess the influence of the prior for each param...

In this paper, multiclass classification problem; One Against All and One Against One, with Least Squares Support Vector Machine (LS-SVM) will be used. There are three type of kernels were used in this paper; Radial Basis Function (RBF), polynomial and linear. One Against All method and One Against One method will be compared to see the accuracy of each kernel, and the amount of misclassification using the confusion matrix. This is illustrated by using iris plant species dataset and the preferred method of contraception dataset. The results showed that the method of One Against One is better than the One Against All based on the accuracy for kernels RBF, polynomial, and linear.

This study considered the problem of predicting survival, based on three alternative models: a single Weibull, a mixture of Weibulls and a cure model. Instead of the common procedure of choosing a single ???best??? model, where ???best??? is defined in terms of goodness of fit to the data, a Bayesian model averaging (BMA) approach was adopted to account for model uncertainty. This was illustrated using a case study in which the aim was the description of lymphoma cancer survival with covariates given by phenotypes and gene expression. The results of this study indicate that if the sample size is sufficiently large, one of the three models emerge as having highest probability given the data, as indicated by the goodness of fit measure; the Bayesian information criterion (BIC). However, when the sample size was reduced, no single model was revealed as ???best???, suggesting that a BMA approach would be appropriate. Although a BMA approach can compromise on goodness of fit to the data (when compared to the true model), it can provide robust predictions and facilitate more detailed investigation of the relationships between gene expression and patient survival.