Search

Although the use of algorithms has become increasingly prominent in the digital market, such algorithms are often opaque and prone to risks of making biased decisions. Algorithms could also be used to harm competition, such as by facilitating cartels. Such developments make it necessary to examine the readiness of existing competition law to tackle cases involving algorithms. This paper focuses on analysing Indonesian competition law to address the following issues: (1) how current Indonesian competition law deals with algorithms-related cases; (2) which indicators could detect anti-competitive algorithms; and (3) which competition policy approach could be considered in Indonesia to tackle the problem resulted from the use of algorithms. [ABSTRACT FROM AUTHOR]

The selection process of new students in educational institutions, such as in Sekolah Menengah Kejuruan (SMK) Wisata Indonesia which still uses conventional methods using paper, has several challenges. One of the main challenges is test cheating, where prospective students may try to manipulate their test results to increase their chances of being accepted. In addition, another challenge faced by SMK Wisata Indonesia is that when the number of prospective students who register is very large, managing answers and exam results can become more complicated. This research aims to design and build an Android-based Academic Potential Test application by applying the Fisher-Yates Shuffle algorithm to randomize the order of questions. This research also uses the RUP (rational Unified Process) system development technique which has several phases, namely the Inception phase, Elaboration phase, Construction phase and Transition phase. The validation testing carried out obtained overall valid results so that the application that has been designed is in accordance with user needs. Meanwhile, usability testing in the Academic Potential Test Application using the SEQ method resulted in an average Likert score for students of 6.63 with a user-friendliness percentage of around 94%. As for teachers, the Likert average score is 6.53 with a percentage of ease of use of around 93%. This shows that the Academic Potential Test Application that has been built is EASY TO USE. [ABSTRACT FROM AUTHOR]

Background: The Dementia Severity Rating Scale (DSRS) is an informant report, dementia staging tool that is quick to administer and has previous been shown to differentiate between people with dementia and healthy controls. However, it is not clear how accurate the tool is screening against diagnostic criteria in middle-income settings. Methods: Embedded within the STRiDE programme, older adults (aged ≥65 years) and their informants were randomly recruited from four sites across Indonesia and South Africa. All informants were asked to complete DSRS. We report the tool's psychometric properties and accuracy against the 10/66 short diagnostic algorithm. Results: Between September and December 2021, data was collected from 2110 older adults in Indonesia and 408 in South Africa. Overall, the DSRS scores significantly differed between those with and without dementia, as identified on the 10/66 short algorithm (p <.05). The difference between groups remained significant after controlling for key factors related to older adult and informant demographics. A score >2 on the DSRS had the greatest agreement with the 10/66 short algorithm and had excellent discriminative properties in both Indonesia (Area Under Curve (AUC) =.75, 95% CIs =.72–.77) and South Africa (AUC =.82, 95% CIs =.76–.88). Conclusions: The DSRS has potential as a screening tool for dementia in middle-income countries, with high sensitivity and specificity against a standardized diagnostic algorithm. [ABSTRACT FROM AUTHOR]

Diabetes Mellitus (DM) is a chronic disease that occurs when the body cannot effectively use the insulin it produces. The use of artificial intelligence (AI) can provide a means to diagnose. This study aims to obtain the best classification of the Naïve Bayes (NB) and K-Nearest Neighbors (KNN) methods so that accurate results are obtained in diagnosing DM disease using a dataset originating from The Abdul Moeis Hospital, Samarinda, East Kalimantan, Indonesia. The results showed that the KNN performed better in accuracy, precision, and specificity with an Area Under the Curve (AUC) value 10% higher than NB. Overall, KNN obtained a better recall compared to the NB in order to DM diagnosis. [ABSTRACT FROM AUTHOR]

Policymakers seeking to target health policies efficiently towards specific population groups need to know which individuals stand to benefit the most from each of these policies. While traditional approaches for subgroup analyses are constrained to only consider a small number of pre-defined subgroups, recently proposed causal machine learning (CML) approaches help explore treatment-effect heterogeneity in a more flexible yet principled way. Causal forests use a generalisation of the random forest algorithm to estimate heterogenous treatment effects both at the individual and the subgroup level. Our paper aims to explore this approach in the setting of health policy evaluation with strong observed confounding, applied specifically to the context of mothers' health insurance enrolment in Indonesia. Comparing two health insurance schemes (subsidised and contributory) against no insurance, we find beneficial average impacts of enrolment in contributory health insurance on maternal health care utilisation and infant mortality, but no impact of subsidised health insurance. The causal forest algorithm identified significant heterogeneity in the impacts of contributory insurance, not just along socioeconomic variables that we pre-specified (indicating higher benefits for poorer, less educated, and rural women), but also according to some other characteristics not foreseen prior to the analysis, suggesting in particular important geographical impact heterogeneity. Our study demonstrates the power of CML approaches to uncover unexpected heterogeneity in policy impacts. The findings from our evaluation of past health insurance expansions can potentially guide the re-design of the eligibility criteria for subsidised health insurance in Indonesia. [ABSTRACT FROM AUTHOR]

The confluence of technological innovations in computation and communications has expanded the scope and increased the intensity of algorithmic applications in markets. Policymakers and regulators are increasingly concerned about tacit collusion among sellers using algorithmic pricing in concentrated markets driven by digital platforms with network effects. Indonesia's competition regulators have expressed similar concerns and noted the need for a greater understanding of the impact of algorithmic pricing, including the detection of anti-competitive business practices. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study focuses on the creation of a novel algorithm for monitoring field data collection activities by field data collection officers from Indonesia's Central Statistics Agency (BPS) using web-based digital technology. This study aims to check the accuracy and veracity of data collected by the BPS data collection officer. In this research, 200 respondents were collected by 10 data collection officers of Indonesia's Central Statistics Agency (BPS) and monitored by 5 supervisors' officers from BPS. Then the Head of BPS supervises process monitoring at a certain regional BPS office. We propose a novel algorithm that can be used with web-based digital technologies. The algorithm is developed by comparing data from the BPS office in the form of three variables that are a list of names of respondents, a list of questioners for respondents, and the location (area) of respondents with data from the respondent's NIK (ID Number), answers to respondents' questions entered into the system, and the GPS location of field data collection officers detected by the web-based system. This research employed a novel algorithm on web-based digital technology, increasing the accuracy and veracity of collected data. The score value of the respondent's name variable is 92 percent, the respondent's answer to the questionnaire variable is 93 percent, and the respondent's location variable is 95 percent. The data was evaluated by all field data collection officers, supervisory officers, and the BPS head. [ABSTRACT FROM AUTHOR]

The Bat optimizing algorithm (BOA) is one of the metaheuristic algorithms and applied here to interpret self-potential (SP) data. The BOA is depending upon a bat echolocation behavior for global optimization, which the global optimum solution reached at the suggested minimum value of the objective function. The best interpretive source parameters for the subsurface structures occurred at the minimal the objective function value (global best solution). The BOA is applied to 2D SP anomaly data to estimate the characteristic source parameters (i.e., the depth to center, amplitude coefficient, origin location, geometric shape factor, and polarization and inclination angle of the causative buried structure). The BOA can be applied to single and multiple source structures in the restricted class of simple geometric shapes, which these bodies help in the validation of the subsurface ore and mineral targets. The stability and efficiency of the proposed BOA have been examined by several synthetic examples. In addition, three different real field examples from Germany and Indonesia have been successfully applied to ore and mineral investigation and geological structure studies. In general, the achieved results are in good agreement with the available borehole data and results mentioned in the literature. [ABSTRACT FROM AUTHOR]

Because of the increasing adoption and use of technology in primary health care (PHC), public health informatics competencies (PHIC) are becoming essential for public health workers. Unfortunately, no studies have measured PHIC in resource-limited setting. This paper describes the process of developing and validating Public Health Informatics Competencies for Primary Health Care (PHIC4PHC), an instrument for measuring PHC workers' competencies in public health informatics. Method: This study developed a questionnaire that had three stages: the Delphi technique, a pretest, and field test. Eleven academicians from a university and 13 PHC workers joined 2 rounds of group discussion in the first stage. The second stage comprised two pilot studies with 75 PHC workers in Semarang Municipality. The third stage involved validating the questionnaire with 462 PHC workers in Kendal District. This study used Pearson's product-moment correlation for the validity check and Cronbach's alpha coefficient for determining the internal consistency. This study used the K-means algorithm for clustering the results of the PHIC4PHC questionnaire. Results and Conclusion: PHIC4PHC is the first comprehensive PHIC questionnaire administered in a resource-limited setting, consisting of 11 indicators and 42 measurement items concerning knowledge of health information systems, skills required for health data management, ethical aspects of data sharing and health information literacy. The final results of PHIC4PHC were clustered into three classes based on the K-means algorithm. Overall, 45.7% PHC workers achieved medium competency, whereas 25.6% and 27.7% achieved low and high competency, respectively. Men had higher competency than women. The higher the worker's level of education, the higher the PHIC level; the longer the worker's work experience, the lower the PHIC score; and the greater the worker's age, the lower the PHIC score. Measuring and monitoring PHIC is vital to support successful health IT adoption in PHC. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID-19) was declared as a global pandemic by the World Health Organization (WHO) on 12 March 2020. Indonesia is reported to have the highest number of cases in Southeast Asia. Accurate prediction of the number of COVID-19 cases in the upcoming few days is required as one of the considerations in making decisions to provide appropriate recommendations in the process of mitigating global pandemic infectious diseases. In this research, a metaheuristics optimization algorithm, the flower pollination algorithm, is used to forecast the cumulative confirmed COVID-19 cases in Indonesia. The flower pollination algorithm is a robust and adaptive method to perform optimization for curve fitting of COVID-19 cases. The performance of the flower pollination algorithm was evaluated and compared with a machine learning method which is popular for forecasting, the recurrent neural network. A comprehensive experiment was carried out to determine the optimal hyperparameters for the flower pollination algorithm and recurrent neural network. There were 24 and 72 combinations of hyperparameters for the flower pollination algorithm and recurrent neural network, respectively. The best hyperparameters were used to develop the COVID-19 forecasting model. Experimental results showed that the flower pollination algorithm performed better than the recurrent neural network in long-term (two weeks) and short-term (one week) forecasting of COVID-19 cases. The mean absolute percentage error (MAPE) for the flower pollination algorithm model (0.38%) was much lower than that of the recurrent neural network model (5.31%) in the last iteration for long-term forecasting. Meanwhile, the MAPE for the flower pollination algorithm model (0.74%) is also lower than the recurrent neural network model (4.8%) in the last iteration for short-term forecasting of the cumulative COVID-19 cases in Indonesia. This research provides state-of-the-art results to help the process of mitigating the global pandemic of COVID-19 in Indonesia. [ABSTRACT FROM AUTHOR]

Stroke is the third most common cause of disability worldwide. In order to effectively study the disability status experienced by stroke survivors, it is important to identify reliable and valid tools to measure disability that can be administered to this population. No previous study had been conducted on the Indonesian version of the WHO Disability Assessment Schedule 2.0 (WHODAS 2.0). The aim of this study was to develop and validate the Indonesian version of the WHODAS 2.0 for stroke survivors in Indonesia. Following translation and back-translation, the Indonesian version of the WHODAS 2.0 was administered to 183 stroke survivors. We used all six domains of the WHODAS 2.0, with the exception of four items of "work or school activities" in domain 5. Internal consistency was measured by Cronbach's alpha, the inter-rater reliability was measured by interclass correlations (ICCs), and the construct validity was tested with an exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). The range of Cronbach's alpha was 0.86–0.92, which indicated excellent reliability, and ICC was very good at 0.87–0.99. The EFA and CFA for the main 32-item questionnaire exhibited a total variance of 95% (KMO) and a p value of <0.05. The factor loadings per items were >0.4, and all the model fit indices were acceptable. The WHODAS 2.0 was adapted for use in Indonesia and showed good results for all six domains. Therefore, the Indonesian version of the WHODAS 2.0 can be applied to assess disability in Indonesian stroke survivors. The WHO Disability Assessment Schedule 2.0 (WHODAS 2.0) was developed as a single, generic instrument for assessing the health status and disability in different cultures and settings. In this study, we adapted and validated an Indonesian version of the WHODAS 2.0 for stroke survivors in Indonesia. The WHODAS 2.0 was adapted for use in Indonesia and showed good results for all six domains. The Indonesian version of the WHODAS 2.0 can be applied to assess disability in Indonesian stroke survivors. [ABSTRACT FROM AUTHOR]

Stemming has been commonly used by some researchers in natural language processing area such as text mining, text classification, and information retrieval. In information retrieval, stemming may help to raise retrieval performance. However, there is an indication that stemming does not hand over significant influence toward the accuracy in text classification. Therefore, this paper analyzes further research about the influence of stemming on tweet classification in Bahasa Indonesia. This work examines about the accuracy result between two conditions by involving stemming and without involving stemming in pre-processing task for tweet classification. The contribution of this research is to find out a better preprocessing task in order to obtain good accuracy in text classification. According to the experiments, it is observed that all accuracy results in tweet classification tend to decrease. Stemming task does not raise the accuracy either using SVM or Naive Bayes algorithm. Therefore, this work summarized that stemming process does not affect significantly towards the accuracy performance. [ABSTRACT FROM AUTHOR]

The application interval type-2 fuzzy inference systems (1T2FIS) has been attention for a short-term load forecasting problems solution. This paper present optimization membership function of antecedent (X,Y) and consequent (Z) interval type-2 Fuzzy Logic System using Big Bang - Big Crunch Algorithm for application short term load forecasting on national holiday. This method has implemented on the historical peak load data during 14 national holiday case study in South and Central Kalimantan - Indonesia electrical power system on year 2008. The Big Bang-Big Crunch (BB-BC) algorithm will applied to optimization interval footprint of uncertainty (FOU) membership functions of interval type-2 fuzzy logic system. BB-BC Algorithm is a global optimization algorithm and has a low computational cost and a high convergence speed, so very efficient in this research. The test result showed main absolute percentage error (MAPE) less than interval type-2 fuzzy inference system (FIS) and type-1 fuzzy inference system (FIS). Finally, this paper defined main absolute percentage error (MAPE) 0.58045% for type-1 FIS, 0.53906% for interval type-2 FIS, and 0.52421% for optimization interval type-2 FIS-Big Bang Big Crunch Algorithm. [ABSTRACT FROM AUTHOR]

Earth observation and land cover monitoring are among major applications for satellite data. However, the use of primary satellite information is often limited by clouds, cloud shadows, and haze, which generally contaminate optical imagery. For purposes of hazard assessment, for instance, such as flooding, drought, or seismic events, the availability of uncontaminated optical data is required. Different approaches exist for masking and replacing cloud/haze related contamination. However, most common algorithms take advantage by employing thermal data. Hence, we tested an algorithm suitable for optical imagery only. The approach combines a multispectral-multitemporal strategy to retrieve daytime cloudless and shadow-free imagery. While the approach has been explored for Landsat information, namely Landsat 5 TM and Landsat 8 OLI, here we aim at testing the suitability of the method for Sentinel-2 Multi-Spectral Instrument. A multitemporal stack, for the same image scene, is employed to retrieve a composite uncontaminated image over a temporal period of few months. Besides, in order to emphasize the effectiveness of optical imagery for monitoring post-disaster events, two temporal stages have been processed, before and after a critical seismic event occurred in Lombok Island, Indonesia, in summer 2018. The approach relies on a clouds and cloud shadows masking algorithm, based on spectral features, and a data reconstruction phase based on automatic selection of the most suitable pixels from a multitemporal stack. Results have been tested with uncontaminated image samples for the same scene. High accuracy is achieved. [ABSTRACT FROM AUTHOR]

Indonesia has a discrepancy between the realized amount and the planned amount of gasoline consumption. This discrepancy has burdened the national budget in Indonesia because this unplanned increase in the imported amount of gasoline has made the government pay more to the importers. The objectives of this research are to develop a robust and accurate model to forecast future gasoline consumption and to provide an attractive alternative model for gasoline consumption forecasting by applying a metaheuristic approach. We apply the harmony search (HS) algorithm for developing a model of gasoline consumption in Indonesia using general socioeconomic variables that can be easily retrieved from public data. The variables used are the gross domestic product (GDP), population, and the total numbers of passenger cars and motorcycles. The HS algolithm selects the optimal weight factors within the proposed exponential model. The results show that the proposed exponential HS algorithm-based model outperforms the conventional nonlinear regression method and particle swarm optimization (PSO)-based model in terms of the mean absolute percentage error (MAPE). [ABSTRACT FROM AUTHOR]

It is widely accepted that an efficient flood alarm system may significantly improve public safety and mitigate economical damages caused by inundations. In this paper, a modified adaptive neuro-fuzzy system is proposed to modify the traditional neuro-fuzzy model. This new method employs a rule-correction based algorithm to replace the error back propagation algorithm that is employed by the traditional neuro-fuzzy method in backward pass calculation. The final value obtained during the backward pass calculation using the rule-correction algorithm is then considered as a mapping function of the learning mechanism of the modified neuro-fuzzy system. Effectiveness of the proposed identification technique is demonstrated through a simulation study on the flood series of the Citarum River in Indonesia. The first four-year data (1987 to 1990) was used for model training/calibration, while the other remaining data (1991 to 2002) was used for testing the model. The number of antecedent flows that should be included in the input variables was determined by two statistical methods, i.e. autocorrelation and partial autocorrelation between the variables. Performance accuracy of the model was evaluated in terms of two statistical indices, i.e. mean average percentage error and root mean square error. The algorithm was developed in a decision support system environment in order to enable users to process the data. The decision support system is found to be useful due to its interactive nature, flexibility in approach, and evolving graphical features, and can be adopted for any similar situation to predict the streamflow. The main data processing includes gauging station selection, input generation, lead-time selection/generation, and length of prediction. This program enables users to process the flood data, to train/test the model using various input options, and to visualize results. The program code consists of a set of files, which can be modified as well to match other purposes. This program may also serve as a tool for real-time flood monitoring and process control. The results indicate that the modified neuro-fuzzy model applied to the flood prediction seems to have reached encouraging results for the river basin under examination. The comparison of the modified neuro-fuzzy predictions with the observed data was satisfactory, where the error resulted from the testing period was varied between 2.632% and 5.560%. Thus, this program may also serve as a tool for real-time flood monitoring and process control. [ABSTRACT FROM AUTHOR]

Statistics have long shaped the field of visibility for the governance of development projects. The introduction of big data has altered the field of visibility. Employing Dean's “analytics of government” framework, we analyze two cases—malaria tracking in Kenya and monitoring of food prices in Indonesia. Our analysis shows that big data introduces a bias toward particular types of visualizations. What problems are being made visible through big data depends to some degree on how the underlying data is visualized and who is captured in the visualizations. It is also influenced by technical factors such as distance between mobile phone towers and the truth claims that gain legitimacy. [ABSTRACT FROM PUBLISHER]

Borneo Island is experiencing rapid tree-cover loss. This loss has been quantified for the Indonesian part of the island at Landsat spatial resolution, but no recent study exists that extends across the border into Malaysia. This research focused on quantifying patterns of tree-cover loss in the Indonesia–Malaysia border zone on Borneo. The methods used for quantifying 2000–2010 tree-cover loss within 20 km on either side of the border are an internally consistent mapping algorithm used on Landsat imagery and a local indicator of spatial autocorrelation to quantify the concentration of loss. Within the 20 km zone on either side of the border, tree-cover loss rates in lowlands were high in the two countries (19.8% and 14.4%, in Indonesia and Malaysia, respectively), but rates in the Malaysian uplands were an order of magnitude higher than in the Indonesian uplands (2.95% and 0.25%, respectively). Clusters of tree-cover loss in the Malaysian uplands were considerably larger than in the Indonesian uplands. [ABSTRACT FROM AUTHOR]

The article presents a study evaluating the implementation of the national tuberculosis (TB) programme's diagnostic algorithm in routine health care settings in Jogjakarta, Indonesia. As mentioned, it was found that 43.5 percent of TB suspects were lost during the diagnostic work-up in health centers and zero percent in lung clinics.

Forest fires in Indonesia mostly occur because of errors or bad intentions. This work demonstrates the application of a decision tree algorithm, namely the C4.5 algorithm, to develop a classification model from forest fire data in the Rokan Hilir district, Indonesia. The classification model used is a collection of IF-THEN rules that can be used to predict hotspot occurrences for forest fires. The spatial data consist of the location of hotspot occurrences and human activity factors including the location of city centres, road and river networks as well as land cover types. The results were a decision tree containing 18 leaves and 26 nodes with an accuracy of 63.17%. Each leaf node holds positive and negative examples of hotspot occurrences whereas the root and internal nodes contain attribute test conditions: the distance from the location of examples to the nearest road, river, city centre and the land cover types for the area where the examples are located. Positive examples are hotspot locations in the study area and negative are randomly generated points within the area at least 1 km away from any positive example. The classification model categorized whether the region was susceptible to hotspots occurrences or not. The model can be used to predict hotspot occurrences in new locations for fire prediction. [ABSTRACT FROM AUTHOR]

This study establishes a new technique for peatland fire detection in tropical environments using Landsat-8 and Sentinel-2. The Tropical Peatland Combustion Algorithm (ToPeCAl) without longwave thermal infrared (TIR) (henceforth known as ToPeCAl-2) was tested on Landsat-8 Operational Land Imager (OLI) data and then applied to Sentinel-2 Multi Spectral Instrument (MSI) data. The research is aimed at establishing peatland fire information at higher spatial resolution and more frequent observation than from Landsat-8 data over Indonesia's peatlands. ToPeCAl-2 applied to Sentinel-2 was assessed by comparing fires detected from the original ToPeCAl applied to Landsat-8 OLI/Thermal Infrared Sensor (TIRS) verified through comparison with ground truth data. An adjustment of ToPeCAl-2 was applied to minimise false positive errors by implementing pre-process masking for water and permanent bright objects and filtering ToPeCAl-2's resultant detected fires by implementing contextual testing and cloud masking. Both ToPeCAl-2 with contextual test and ToPeCAl with cloud mask applied to Sentinel-2 provided high detection of unambiguous fire pixels (>95%) at 20 m spatial resolution. Smouldering pixels were less likely to be detected by ToPeCAl-2. The detected smouldering pixels from ToPeCAl-2 applied to Sentinel-2 with contextual testing and with cloud masking were only 35% and 56% correct, respectively; this needs further investigation and validation. These results demonstrate that even in the absence of TIR data, an adjusted ToPeCAl algorithm (ToPeCAl-2) can be applied to detect peatland fires at 20 m resolution with high accuracy especially for flaming. Overall, the implementation of ToPeCAl applied to cost-free and available Landsat-8 and Sentinel-2 data enables regular peatland fire monitoring in tropical environments at higher spatial resolution than other satellite-derived fire products. [ABSTRACT FROM AUTHOR]