Search

Senior Citizen is an elderly human in a golden age who has many limitations. The number of older people is increasing in almost every country, including in Indonesia. One of the diseases that were suffered is senile or known as Dementia. Therefore, to protect the elderly, the special care is needed in order to be able to monitor the located and to see the condition of the elderly when they are travelling outside the home. Based on that condition, a prototype of the detector is proposed in this paper namely Smart tracking for the Golden Age's Citizen. This system consists of a GPS module, a vibration sensor, a GSM Module, and a voice recorder module. GPS module will detect the location, and the vibration sensor will detect the vibration if the elderly falls. The GSM module will send the information in the form of SMS to the family. The voice recorder module is used to record and play the recorded sound. Based on the results of the prototype test, the prototype is successfully detecting the location if the elderly is outside the range. The testing was concluding that the older people position can be tracked approximately around 2-5 meters from the determination in google map application and send an SMS in 3-5 seconds, if the user falls or lost. [ABSTRACT FROM AUTHOR]

COVID-19 was declared a world pandemic in early-mid 2020. After about a year, several vaccines for this virus have been found and become alternative solutions to reduce the spread of the COVID-19 pandemic and build up herd immunity in society. Since early 2021, Indonesia has been one of the countries that participate in using vaccines for the public to fight the COVID-19 pandemic. However, there are a lot of positive and negative responses from Indonesian society related to these COVID-19 vaccines. Implementing a sentiment analysis model for a specific topic like a "vaccine" from social media could help us to see and understand the responses from society in Indonesia towards the vaccine program that is being conducted by the Indonesian government. Understanding society's response towards vaccines is expected to be able to support the Indonesian government, for example in formalizing the distribution strategy of vaccines in the future. This paper discusses how to develop a sentiment analysis model, by implementing several existing technologies such as Twitter API, TextBlob , and Googletrans Python libraries. The utilization of these existing technologies could show how a sentiment analysis model could be developed conveniently, for example in using cases to analyse Indonesian society's responses towards the COVID-19 vaccine program. Besides the solution design, this paper also shows a sample of data visualization of the sentiment analysis model in a meaningful infographics format. [ABSTRACT FROM AUTHOR]

Numerous research on stunting supplementation interventions in Indonesia have been published. The information can be extracted through data mining, especially from academic research databases. In this paper, we presented a text mining-based literature review strategy to create a pipeline that researchers can use to accelerate the development of stunting supplementation intervention research in Indonesia. Utilizing various NLP (Natural Language Processing) techniques, data were crawled, processed, and visualized using Python. The crawling dataset used a module from the Pubmed API (Application Programming Interface) to collect literature papers. The NLTK (Natural Language Toolkit) module and itertools were used to process text data. The n-grams model was applied to process tokens into bigrams and trigrams. Text information was visualized using Matplotlib and Word cloud packages. There is an increasing number of publication in stunting supplementation intervention according to our result, which was observed from 2015 to 2021. West Java was the province where most of the stunting research has been conducted, as determined by research abstracts. Top occurrences obtained from the bigram and trigrams models calculation produced different terms. The word pairings that occurred the most frequently in the bigram and trigram model analyses were "child-aged" and "iron-folic-acid," respectively. The findings of this study are expected to help researchers to obtain the latest research topics related to stunting supplementation interventions in Indonesia. [ABSTRACT FROM AUTHOR]

COVID-19 pandemic affected many aspects in global life, the one of aspect is e-commerce. The COVID-19 pandemic changes the general society into having a more consumptive behavior. This research is conducted to identify whether there is a difference in mean/average sales between the period before the COVID-19 pandemic and during the COVID-19 pandemic. This paper used T-Test Paired Samples to analyze the difference of behavior's customer of some e-commerce in Indonesia. Biplot analysis is also used to give visualization of the behavior's change caused by the COVID-19 pandemic. Six variables are used in this paper and purposive sampling is selected to get a sample size. We use 63 respondents are eligible to fulfill the questionnaire. The T-Test paired samples resulted that there is a difference in mean sales for the service or online products, food and beverages, electronics, and cosmetics and skincare. Those aspects are evidence that COVID-19 pandemic could change the customer behavior in E-Commerce. We also illustrate the change of customer behavior through biplot [ABSTRACT FROM AUTHOR]

Higher education institutions in Indonesia are required to report their academic data to the national higher institution database (namely PDDikti) through a synchronization mechanism. Because the PDDikti database has been used as the reference for nationwide programs such as university ranking, diploma verification, faculty promotion, and tenure, academic data in their reports have to be valid, accurate, and up to date. Yet, data quality is an issue among higher institutions, while data governance is the heart of data quality. This paper investigates challenges encountered by a public university in Indonesia in implementing data governance and how to resolve them. The findings outline six main challenges in data governance implementation. [ABSTRACT FROM AUTHOR]

This study aims to predict the determinants of mobile fintech apps and digital financial inclusion from the perspective of the Bottom of the Pyramid (BOP) segment in Indonesia. To address the complexities of BOP users, this paper theoretically grounded on Mobile Technology Acceptance Model (MTAM) (i.e. mobile usefulness (MU), mobile ease of use (MEU)) along with its relevant extension including personal factor (digital financial literacy (DFL)), financial risk factor (mobile perceived financial cost (MPFC)), and consequent factors (i.e. use behavior (UB), and digital financial inclusion (DFI)). The moderating impact of gender was also tested. A survey instrument that was self-administered and comprised measurement items adapted from prior research was utilized to gather data from 200 mobile fintech BOP users residing in Makassar, South Sulawesi. According to the results of the PLS-SEM test, seven hypotheses were accepted, while two were rejected. In addition, it was confirmed that men play a more prominent role than women in strengthening mobile fintech use and digital financial inclusion. [ABSTRACT FROM AUTHOR]

Temporary trade barriers, such as safeguards, is a measure to rescue the economy in such a way as to protect domestic industries from foreign competitors. Safeguards provide opportunities for domestic industries to make structural adjustments and reshape their business process to increase their competitiveness during the validity period. Indonesia's government has imposed safeguards for most textile sub-industries, from the upstream industry (yarn and fibres) to the downstream garment industry and other related textile industries. This paper aims to evaluate whether the application of safeguards meets its objectives in improving the competitiveness of domestic industry against its foreign competitors with a long observation period. It is found that the effectiveness of the application of safeguards was limited to rescuing the trade balance. In terms of export competitiveness, safeguards have not been effective in increasing the export competitiveness of the textile industry in the world market. [ABSTRACT FROM AUTHOR]

As start-up companies may leverage information spreading through Instagram's hashtag-setting, algorithms in influence maximization can be encoded. The objective is to find a maximum impact which can activate users in spreading advertisement marketing campaign through social network. This paper contributes an influence analysis on Instagram and reproduces it into a hashtag network by transforming postings with hashtag interdependence. In finding optimal paths such network structure with influence probabilities, we employ Floyd-Warshall algorithm under uncertainty. The technique is simulated on Indonesian FnB unicorn company and demonstrated in numerical example. The result shows that the hashtag #promokopi may impact the most. [ABSTRACT FROM AUTHOR]

This paper proposes the development of a markerless augmented reality (AR) application for Indonesian traditional house education. The application aims to provide an immersive and interactive way of visualizing traditional houses from various regions of Indonesia, with the potential to raise public awareness about the importance of preserving traditional culture. The prototyping method was employed as the most appropriate approach to software development, and the ARFoundation platform was used to integrate plane detection into the AR application. The results showed that 80% of tested devices were compatible with ARCore, and the AR plane detection could detect up to 250cm from the device position. In addition, a feedback survey conducted on 17 testers showed that the application design and mechanism brought a good experience to users, with 53% stating that the app is easy to use. This research project contributes to the development of technology-based solutions to promote Indonesian culture and preserve traditional houses, especially for younger generations who may be less familiar with traditional culture. [ABSTRACT FROM AUTHOR]

People with hearing impairments exist in our society, whether we realize it or not. It is not easy for them to communicate with us, the ones without hearing disabilities, and they often receive a lot of mistreatment. Since we don't learn about sign language and don't know where to start, our knowledge about sign language is also limited. This paper explains the making of Deafvoir—a visual novel game about sign language—as well as why it is developed and how it can help the deaf and us learn sign language. By conducting a survey and asking how familiar sign language is to some people and their response about Deafvoir, we can move forward to realize this sign language learning visual novel video game and make it local-based before going international. With this video game, it is hoped to make Indonesia's younger generation, especially Gen Z, understand and be able to use sign language whenever they encounter the deaf in real life. [ABSTRACT FROM AUTHOR]

Indonesia is a vast market for talents recruiting, with around 203 million people that count into work age definition (above 15 years) and around 138 million of them are workforce, while 7 percent of the workforce are open for hire. There are several players of job-seeking apps in Indonesia. But most of them are targeting talents with undergraduate degrees and above. Mid to high-level jobs have become such an attractive market for these players. We can see it on several job seeker hub websites, where job seekers proudly post their personal profiles to attract recruiters from top employers. It is not possible for lower-level job seekers to post their profiles on these websites. They will just be under the recruiter's radar. Whereas from the report data released by the Indonesian statistical center bureau regarding the percentage of open unemployment based on education level, the total unemployment rate from diploma education and below is very large compared to the unemployment rate with university education (undergraduate and above). The Covid-19 pandemic also gave a negative impact on the lower job segment, with a decrease in demand and sales resulting in a higher layoff rate which also means an increased percentage of the open unemployment rate. We need a solution to this problem. A solution that can erode a large chunk hidden under an iceberg. This paper offers "Megawe", a mobile application-based solution to assist both job seekers and low-level job recruiters. This segment may have a smaller contract value than upper segments but has a much larger quantity of labor force. Because we are focusing on development speed and accuracy of requirements, we used the prototyping methodology in the implementation of the solution. Moreover, before it is launched publicly, we conducted usability testing to gain a deeper understanding of the user experience directly from users of the targeted segment. [ABSTRACT FROM AUTHOR]

Classification of Indonesian crops is a critical task in developing farming and getting more understanding of agriculture. However, there is no clear task in classifying types of crops in Indonesia. Transfer learning has been used successfully in a variety of image classification applications. Thus, in this paper, we collected images of Indonesian crops from the internet randomly and proposed a classification by using transfer learning of deep learning with four pre-trained models: EffficientNet- B0, ResNet18, VGG19, and AlexNet. In the experiment, augmentation techniques such as random horizontal flip, random vertical flip, and random affine were utilized to prevent the network from overfitting. The result found that EfficientNet-B0 outperformed other models with an accuracy of 82.55. Then, the model struggled to distinguish between crops in the same family. According to the results, although transfer learning can work well to classify images of Indonesian agricultural crops, some improvements are still required to address existing issues. [ABSTRACT FROM AUTHOR]

The writing of this paper and the creation of this application is a means to improve and add on facilities on the local state-run attraction. This subject matter was picked in conjunction with the decline of tourism in the said historical site due to a pandemic that rankles Indonesia's tourism industry and drives it to the ground. Augmented Reality as a method of deliverance was picked due to its popularity and freshness in the tourism market. The research method was conducted starting with analysis, development, implementation, then evaluation. Analysis was done using sourcing available to the public and a questioner. Implementation was done using Unity, Vuforia, and Maya. And with the positive responses of 66.6 percent of the sample market finding enjoyment in the use of this application in their exploration during User Acceptance testing with the existing prototype. This shows that the resulting use of this application improves user enjoyment in experiencing the state attraction. [ABSTRACT FROM AUTHOR]

In recent years, technology has advanced so much that it is so widespread and the internet is being used by 53.7% of Indonesia's population. This paper reviewed how privacy violations occur, their potential impacts, and their prevention methods personally such as individuals and organizations through literature review. Overall, it can be concluded that in general. There are two methods to prevent privacy violations, which are by using computer security software and end user awareness training. [ABSTRACT FROM AUTHOR]

Technology development has been getting more advanced and greatly facilitated human life. One of them is machine learning automation which has been proven to be consistent for doing various computations against extensive data such as transaction data in the e-commerce area. Seeing this opportunity, we implemented the machine learning approach to detect fraudulent cashback transactions in e-commerce that are currently rife in Indonesia. The training data used to build the machine learning model were the transaction data from one of the leading e-commerce in Indonesia that had been processed. The supervised classification algorithms used were K-Nearest Neighbor (k-NN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM). In the end, the best steps and methods that could be taken against fraudulent cashback activities in the future are shown in this paper. [ABSTRACT FROM AUTHOR]

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-the-art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification. [ABSTRACT FROM AUTHOR]

Nowadays, social media is considered as an essential tool for an organization to communicate with another user, customers and potential customers for gaining popularities, getting ideas and opinion from the users, or affecting another user. One of the problems on social media is the uses of the social bots, that used to make a human user believe the opinion generated from the social bots. These bots can use their ability to post in higher rates than human user to shift the topic that discussed in the time being. To resolve the problems on social bots, there are several ways to identify a bot from an account such as checking the date of account creation and interval on creating between posts with using machine learning.in this paper we will discuss what is the best machine learning algorithm to determine a social bot, and which feature that helps the algorithm the most. In our work, the data that will be used from Indonesia President Candidate's Supporter's Tweets from each side, Joko Widodo (@jokowi) as the first candidate and Prabowo Subianto (@prabowo) as the second candidate from a month. The algorithms that will be used on this paper are Support Vector Machine and Random Forest with cross-validation as a training method. We found that the year of account created has the highest contribution to bot detection. [ABSTRACT FROM AUTHOR]

This paper puts Indonesia in the spotlight assessing the country's ability to combat corruption through ICT enabled governance. The research firstly tries to define governance through the different lens of intergovernmental organisations. This is followed by a comparative analysis of different situational characteristics of governance in developing and developed countries. The paper then explores the role of governance in Indonesia, highlighting the existing barriers, and potential drivers to the implementation of ICT in Indonesia. It is concluded that ICT enabled good governance needs to be in place to support the eradication of corruption in Indonesia. Corruption in Indonesia is considered systematic as the practice is prevalent across public organisations in the country. This study contributes to the information systems discipline by offering new insights into the issues of implementing ICT enabled open governance in developing countries such as Indonesia. [ABSTRACT FROM AUTHOR]

eXtensible Business Reporting Language (XBRL) is a significant new information technology for the electronic communication of business and financial data. XBRL has been implemented by Central Bank of Indonesia and Indonesia Stock Exchange but not yet adopted by Indonesian Tax Authority. As there was no data exchange among the regulators, it may result in inconsistent financial information among these authorities. However, before promoting this G2G sharing, the tax authority has to adopt the XBRL in the first place. This research proposed the XBRL taxonomy, which can be used in the adoption of XBRL for the e-Tax Corporate Filing system. As an applied research, the paper technically demonstrates how to develop XBRL taxonomy called The Corporate Tax XBRL Taxonomy (1771-CTXT). The taxonomy was created based on the iterative approach as the main part of the Design Science Research (DSR) process model. Although this research paper was done based on the case study of corporate income tax in Indonesia, the steps to developing taxonomy document could be applied as well to other countries' tax regulators. In implementing XBRL based data exchange among regulators, the National XBRL taxonomy has to be developed first to provide XBRL elements, which can be re-used among them. The XBRL extensions of the national taxonomy should also be developed for particular reporting domains such as tax and statistics. [ABSTRACT FROM AUTHOR]

This paper aims to determine the impact of accelerating duration on profits and contingency cost.The method using infrastructure project building in Surabaya Indonesia 2020 historical data set, followed by System Dynamic (SD) modeling and ending with a scenario of the relationship between project duration acceleration, addition profits and crashing cost.Project acceleration can improve project performance by considering the effect on profits and contingency costs,with Schedule Performance Index (SPI) up to 1.06 can increase profit between 1.05%-4.72% due to reduced in indirect costs,otherwise crashing cost will reduce contingency cost between 0.43%-1.91% of the contract value. [ABSTRACT FROM AUTHOR]

Coronavirus disease is a worldwide pandemic. The need for accurate data and information become an important thing in this pandemic situation. In Indonesia, the government provides an official website for displaying COVID-19 spread statistics. However, the data provided does not follow the 5-star open data. As a result, the data is not reusable and integrated easily into another dataset and application. In this paper, we proposed an RDF vocabulary for presenting COVID-19 data in Indonesia. In addition, two queries are presented as an example for using our vocabulary and dataset as part of Linked Open data movement. [ABSTRACT FROM AUTHOR]

Motive is an important underlying reason an organization engages in a particular behavior, which includes initiating a particular information systems adoption. Adoption motives, however, are situational, urging motivational studies to be contingent on the context. The purposes of this paper are therefore twofold: (1) reflecting on the case of Indonesian e-voting initiative, to examine the local government’s motives behind e-government adoption; (2) to identify emerging themes that might have influenced the process of e-voting adoption in several Indonesian villages. Qualitative data were collected from five government leaders at both municipal and village levels in a municipality that have previously conducted village e-voting elections. This study found that performance-related rationalities, i.e. cost-savings, reducing service delivery-time, are the main drives for e-voting adoption in this case. Although instances of motives belonging to technological and strategic clusters have also been recorded, none of the leaders responded to operation-related motives. This might be due to the simplistic interpretation of e-voting as merely a replacement for paper-ballots, while its broader implication to democratic values and election best practices have been largely ignored. Moreover, it was evident from the study that the decision to adopt voting technology in this case has been significantly influenced by political interests, where strong cases of leadership further accelerated the adoption process. The strong determination exhibited by higher level leaders has put significant pressures on the lower level authorities to implement e-voting, which might have conflicted with their own organizational strategy, socio-cultural norms, and citizen preparedness. This study is important to identify context-based rationales behind e-voting initiatives in Indonesia and the results are relevant to assist Indonesian government in the development of other e-government strategy in the future. This paper further emphasizes for a broader strategy which takes account of the risks of impairing democratic values and generating conflicts during electoral processes. [ABSTRACT FROM AUTHOR]

Recognizing Textual Entailment (RTE) is a Natural Language Processing task to determine whether a sentence (text) semantically entails another sentence (hypothesis). In this paper, we extracted and learned 35 features from a pair of text and hypothesis in Indonesian. The ablation study was conducted to analyze features contribution to RTE model. The experiments shown that, using Support Vector Machine (SVM) and Logistic Regression, the token-based features contribute positively to improve the model performance. The best model in our experiment is SVM that scored F1-Score of 79.65%. Despite sacrificing 5-points accuracy to the state-of-the-art BERT model, SVM classifier is 31 hours more efficient in terms of training time. [ABSTRACT FROM AUTHOR]

The sentiment classification method is a research field that is proliferating in Indonesia since it is fast in extracting public opinion and provides essential and valuable information for stakeholders. Of the best-performing sentiment classification approaches, machine learning is one of them that has excellent performance. However, the method has several problems, such as noisy features and high dimensionality of features that significantly affect the sentiment classification performance. Therefore, to overcome the problems, this paper presents a novel feature selection using a combination of Query Expansion Ranking (QER) and Genetic Algorithm-Support Vector Machine (GA-SVM) for improving sentiment classification performance. Based on the experimental results, the proposed method could significantly improve sentiment classification performance, outperform all state-of-the-art algorithms, and decrease computational time. The method achieved the best performance in average precision, recall, and f-measure with the value of 96.78%, 96.76%, and 96.75%, respectively. [ABSTRACT FROM AUTHOR]

Today, Indonesian citizen experience a fast changing lifestyle related to information and communication technology (ICT) utility, such as gadget and internet. The ease of information and knowledge retrieval to support learning process comes with problems to be taken care of such as information overload, negative content, netiquette negligence, and gadget addiction. Meanwhile, Indonesia will face an upcoming challenge in the economic sector, Free Trade Area of the Asia-Pacific (FTAAP) in 2020. An initiative for economic integration uses ICT as economic hub to promote every sector growth in economy. A concept explored in this research context to answers those problems mentioned above and to overcome the upcoming challenge is improving quality of Indonesian human resources through digital literacy education. This paper discusses a learning system model dedicated to deliver digital literacy education to the Indonesian citizen. Objectives of this research are increasing awareness towards digital literacy concept and preparing citizen to be digitally literate and competent using ICT to support their learning process, doing their work more effective and efficient, and preparing Indonesian young generation to become qualified workforce competing in FTAAP 2020, furthermore international work competition. This paper delivers analysis for learning system model as a result from the initial research of research series about digital literacy education in Indonesia. Resulting model justified by sets of detailed scenario about how this model works. [ABSTRACT FROM AUTHOR]

Learning history means to learn what caused the world around us to become the way it is right now. For decades, historical events were recorded and taught to younger generations to learn from them. However, most students found that learning history is boring because they could not feel or understand the moment of those historical events. This paper aims to investigate how a game-based learning approach influences the achievement and motivation of historical learning through a mobile learning environment. We propose game-based historical learning using the role-playing game on a mobile platform. The implementation is based on the history of the first army general in Indonesia, General Sudirman. The game was tested to 63 Junior High School students in Jakarta. Based on the evaluation, using the game can increase student learning motivation and learning achievement. [ABSTRACT FROM AUTHOR]

COVID-19 is a virus causing pneumonia, also known as Corona Virus Disease. The first outbreak was found in Wuhan, China, in the province of Hubei on December 2019. The objective of this paper is to predict the death and infected COVID-19 in Indonesia using Savitzky Golay Smoothing and Long Short Term Memory Neural Network model (LSTM-NN). The dataset is obtained from Humanitarian Data Exchange (HDX), containing daily information on death and infected due to COVID-19. In Indonesia, the total data collected ranges from 2 March 2020 and by 26 July 2020, with a total of 147 records. The results of these two models are compared to determine the best fitted model. The curve of LSTM-NN shows an increase in death and infected cases and the Time Series also increases, however the smoothing shows a tendency to decrease. In conclusion, LSTM-NN prediction produce better result than the Savitzky Golay Smoothing. The LSTM-NN prediction shows a distinct rise and align with the actual Time Series data. [ABSTRACT FROM AUTHOR]

Dengue fever is a disease caused by the dengue virus, which is spread by Aedes aegypti and Aedes albopictus mosquitoes. According to the WHO, as a tropical country, Indonesia is a country at high risk for dengue. Dengue can spread to other people through mosquito bites. Weather factors, such as temperature, humidity, and rainfall, affect the number of dengue incidents. It is important to predict the number of dengue incidents so that the government and the people will be ready to prevent a dengue outbreak when the number of dengue incidents is predicted to be high. In this paper, we predict the number of dengue incidents in DKI Jakarta using support vector regression, with weather and the previous number of incidents as predictor variables. These predictor variables are determined by analyzing the time lag between each predictor variable and the number of incidents by using cross-correlation. Models for prediction are compared by Root Mean Squared Error and Mean Absolute Error. The result shows that support vector regression with linear kernel is quite good, and is in fact better than the radial kernel, for predicting the number of dengue incidents. [ABSTRACT FROM AUTHOR]

Economic performance is one of the important things that have to be evaluated by the government. There are many factors that affect economic performance. This paper aims to evaluate the effect of fiscal decentralization indicators on regional economic performance in Sumatra Island, Indonesia. Based on the results of spatial dependency testing, can be concluded that there are spatial dependencies on economic performance and spatial heterogeneity between locations in Sumatra Island. Therefore, Geographically Weighted Regression (GWR) which is a spatial modelling can be used in this case. There are six independent variables that be used in this research, there are original local revenue, general allocation fund, special allocation fund, and profit share fund, poverty rate and human development index. The result showed that Geographically Weighted Regression model performed better than multiple linear regression of Ordinary Least Square (OLS) model, providing different effect information at each location. Based on model evaluation using RMSE, MAPE and AIC showed that GWR model is better than OLS model. [ABSTRACT FROM AUTHOR]

Rainfall is one of the climate components which is very important for an agrarian country with a tropical climate like Indonesia. There are so many variables that can affect the intensity of rainfall, including humidity, air temperature, speed and wind direction. However, not all of these variables can have a significant effect, therefore, we need a modeling technique that can select and shrink the predictor variables so as to make the model simpler. One of the techniques used is the Lasso (least absolute shrinkage and selection operator). The purpose of this study is to model rainfall intensity using lasso regression and determine which variable have the greatest influence on rainfall intensity. This paper also designs an application system that can be used to implement Lasso regression. The response variables in the form of daily rainfall at the Citeko observation station, Bogor Indonesia is assumed to have normal distribution. Rainfall intensity modeling involves 16 predictor variables, namely the maximum temperature, minimum temperature, average temperature, average humidity, sun exposure, maximum wind speed, wind direction when maximum wind speed and 8 other categorical variables are the most frequent wind direction. The resulting Lasso regression model successfully select and shrink the variables used to 9 variables only. In addition, based on the AIC and coefficient of determination indices for the model evaluation, the Lasso regression shows satisfying results rather than classical multiple linear regression. In Lasso regression, AIC value is 5901.20 where in classical model it is 5911.43. Also, Lasso regression coefficient of determination value is greater that is 22.73% while in classical model is 21.41%. From lasso regression model that has been obtained, it is known that the most frequent wind direction to the north is the variable that has the greatest influence on rainfall intensity. The Lasso regression application has been successfully created so that it can facilitate the user in uploading data, exploration of data and variables, Lasso regression analysis and report result. [ABSTRACT FROM AUTHOR]

Adopting a deep learning model into bird sound classification tasks becomes a common practice in order to construct a robust automated bird sound detection system. In this paper, we employ a four-layer Convolutional Neural Network (CNN) formulated to classify different species of Indonesia scops owls based on their vocal sounds. Two widely used representations of an acoustic signal: log-scaled mel-spectrogram and Mel Frequency Cepstral Coefficient (MFCC) are extracted from each sound file and fed into the network separately to compare the model performance with different inputs. A more complex CNN that can simultaneously process the two extracted acoustic representations is proposed to provide a direct comparison with the baseline model. The dual-input network is the well-performing model in our experiment that achieves 97.55% Mean Average Precision (MAP). Meanwhile, the baseline model achieves a MAP score of 94.36% for the mel-spectrogram input and 96.08% for the MFCC input. [ABSTRACT FROM AUTHOR]

NonCommunicable Diseases (NCDs) have been the public concern worldwide, both in developed and developing countries. The issues are not only about the number of mortality but also the economic implications caused by the diseases. This paper aims to exploit the mobile technology potential by developing an mHealth medical record to assist the prevention and controlling of diseases in Indonesia, particularly in the West Papua Province. Design Science Research (DSR) methodology in Information System (IS) is employed to guide these research activities. This solution enables the medical data to be deposited by a person directly and personally utilising the developed mHealth application installed in the smart phone. By the time that person needs a further health examination for the NCD symptoms, the deposited data allows a General Practitioner (GP) making decision relatively easier at the first place. Some issues have been identified: data integrity and reliability as well as the manual assessment by the GP. Therefore, further evaluations are sought. [ABSTRACT FROM AUTHOR]

This paper presents a conceptual model to analyze motivation factors and perceived risk factors of open data measurement in Indonesia local government. The conceptual model is developed from a theoretical background and literature reviews of related research, which describes open data government, indicators of open data measurement, motivation factors and perceived risks factor in open data. In result, there are eight factors that construct in the model. There are four motivation indicators and four perceived risk indicator that influence open data measurement. For each indicator are determined from the literature review and previous research. In the future, the conceptual model is expected to be able to provide insight to Indonesian local governments on open government data through an analysis of the relationship of identified motivational factors and perceived risks factors. [ABSTRACT FROM AUTHOR]

Health information systems (HIS) in developing countries constantly face human resource-related issues such as low capacity and high staff turn-over. When combined with high national demands, it is even more difficult to address with limited capacity building resources such as trainers and financing. This research aims to explore the potentials of digital learning tool as part of a national HIS capacity building strategy, drawing from a case from Indonesia. The country is adopting District Health Information Software (DHIS2) to integrate health data and to promote quality health information use. DHIS2 implementation will be expanded to 463 districts by 2022. As the consequence, the country needs efficient tools and strategies to build capacity to fulfill this need. A joint team consisting of MoH, Universitas Gadjah Mada (UGM) and University of Oslo (UiO) localized a global digital learning platform called DHIS2 Online Academy and successfully recruited 627 learners and graduated 150 learners. Although approximately half of the responding learners claimed to have no past online learning experience, nor DHIS2 experience, they reported that they found digital learning materials convenient for them to improve their competencies in DHIS2 implementation, in terms of time, cost, and learning style. DHIS2 Online Academy Indonesia allows wider delivery of DHIS2 learning materials to health workers, supporting HIS strengthening at district and facility level. This paper discusses potentials and challenges of localization of generic learning platform and its integration to national capacity building strategy, summarizes the key principles and the way forward. [ABSTRACT FROM AUTHOR]

National Archive Information System and National Archive Information Network (SIKN JIKN) is a national priority program agenda of National Archives of the Republic of Indonesia (ANRI) as an archival institution. To support management and operation of SIKN JIKN, ANRI provides national helpdesk service. A helpdesk application is provided to help their duties, but it is not used optimally that caused the risks such as loss of data and requests or problems submitted by SIKN JIKN members as a user of the system. If the risk is not handled, it will cause losing of potential network node as well as the loss of ANRI. In this research paper, performed risk assessment of SIKN JIKN helpdesk activities was done by referring to COBIT 5 for Risk and COBIT 5 Enabling Process as guidelines, framework, and focusing in domains to support helpdesk activities which is DSS01 domain for operational procedures and APO12 for managing risks. The result of assessment may be used as a recommendation to improve helpdesk service to support SIKN JIKN implementation. It is also could minimize the risk impact to ensure the sustainability of helpdesk service of SIKN JIKN. [ABSTRACT FROM AUTHOR]

Fuzzy ELECTRE (Elimination Et Choix Traduisant la Realité) is one of the fuzzy multi criteria decision making methods for resolving the ambiguity of concepts that are associated with decision maker's judgments. In this paper, the proposed methods are applied to a construction company in Indonesia, that is the fuzzy ELECTRE method is applied to cement vendors recommendation problem of PT Wijaya Karya. There are four vendors (A1,A2,A3 and A4) as a recommendation for the best vendor selection. The selection of vendors of raw materials is one of the activities in supply chain management at PT Wijaya Karya. The role of the vendor will contribute to determining the success of this company. After determining the criteria that affect the vendor selection decisions, the results for fuzzy ELECTRE methods are presented. [ABSTRACT FROM AUTHOR]

Recently, horticulture farming, especially in Indonesia, are facing various obstacles, including the lack of young farmers regeneration, agricultural land decreasing, and climate change. Climate change increase extreme and uncertain weather for horticulture cultivation. Farmers frequently face frequent damage to crops and decreasing in quantity and quality of plants. The development of a monitoring system that can help farmers grow crops is a crucial issue. In this paper, a study for a system for monitoring the performance of indoor micro-climate horticulture is presented. An electronic sensors Internet-of-Things (IoT) board is implemented to monitor the cultivation process. The sensor reading is collected into a database. The database is also integrated with the Indonesian Meteorological Agency data which consists of weather data and daily at the cultivation location. For our future work, the collected data are expected to be used for training machine learning models for the development of intelligence automated indoor micro-climate horticulture. [ABSTRACT FROM AUTHOR]

Places classification is one of the points of discussion in the computer vision and robotics community. Some renowned techniques such as local-invariant feature extractors (e.g. Scale-invariant feature transform SIFT, Speeded Up Robust Features SURF), as well as Visual BoW approach were used in place classification problems. Nowadays, deep learning methods such as Convolutional Neural Networks (CNNs) have the advantages towards computer vision problems including place classification problem. Albeit, there are several renowned datasets existed to help the community to learn the models, there is no publicly exists in places dataset for specifically places in Indonesia. This paper presents methodology to collect data of visual places in Indonesia, learn deep features from the data, and classify visual places in Indonesia. We aims to contribute a large dataset as well as deep learning models of places in Indonesian. There are more than 16K images collected and augmented to build the places (specifically places in Indonesia) dataset. The highest accuracy score achieved by the models is 92%. [ABSTRACT FROM AUTHOR]

Currently in most cases, the inference of spatio-temporal modeling using Bayes regression still utilize MCMC simulations, which has an important issue in their limitation in computational burden. Involving big datasets, the complexity of Bayes spatio-temporal modeling could lead inefficient performance from Bayesian inference via MCMC. This paper aims to predict rainfall in observed and unobserved locations using Bayes spatio-temporal model with the inference of INLA, which has proven capable of providing fast and accurate results. The response variable is monthly rainfall from 57 locations in West Java Indonesia, observed from 1981 – 2017 and assumed to have normal distribution. Our spatio-temporal modeling based on additive framework, which can capture the spatial and temporal random effect as explanatory variables. The spatial random effects are a realization of Gaussian process with spatial dependency follow Matérn model, and the temporal random effects are assumed to have annually cyclic and follow random walk of order two. The model shows satisfying results: the spatio-temporal model able to predict rainfall even for unobserved locations using the spatio-temporal characteristics from nearly locations with the correlation between predicted and real data sets is about 0.7 – 0.8 for high to low quantile with RMSE is about 294 for high quantile. [ABSTRACT FROM AUTHOR]

Statistical Downscaling (SD) is a model that uses satellite data from General Circulation Models (GCM), which in climatology are very useful in predicting climate for the next few decades. GCM data is generally ill-conditioned, which is high dimension and multicollinearity, so a special technique is needed to handle this poorly conditioned. One of the variable selection techniques and handling of multicollinearity which is currently highly developed is regularization techniques including Adaptive Lasso, where selective parameters are adaptive, which can differ for each regression coefficient. Until now, predictions of extreme rainfall in Indonesia have not used Adaptive Lasso in SD modeling. This paper aims to predict the amount of rainfall (in millimeters) at moderate extreme (quantile 0.75) and high extreme rainfall (quantile 0.9 da 0.95) and handling poorly conditioned GCM data with Adaptive Lasso techniques and building predictive models of local rainfall by utilizing GCM data using the Bayes quantile regression model. Response in the form of monthly rainfall at Indramayu district, West Java Indonesia, and 49 explanatory variables in the form of GCM precipitation data in the period January 1981 - December 2013, which handled multicollinearity and variable selection using the Adaptive Lasso. The results are very satisfying with correlation between predicted and real data is above 0.91 for and the RMSEP is less than 50. [ABSTRACT FROM AUTHOR]

Recently there has been an interest in predicting complex disease risk using models that combine the effects of many genetic factors together. These are known as polygenic models and are useful in evaluating risk of disease in patients. These models, however, often do not include important non-genetic factors that are important to the prediction of the disease. In this paper, we explore the prediction of colorectal cancer in Indonesia from non-genetic factors using common machine learning algorithms: XGBoost and Elastic Net. The result of this study identified 8 features with strong importance from both XGBoost and Elastic Net. We recommend including these features as covariates in future genetic association studies of colorectal cancer in Indonesia. Ultimately these models may be implemented as tools to screen patients for colorectal cancer risk. [ABSTRACT FROM AUTHOR]

This paper propose a serious game to teach social critique to adults with a desktop horror myth game, as the moral story of the myth fits to the social subject to teach to the player/learner. Social problems have been an interesting subject to talk, discuss, and debate in all around the world. This due to the wave of change and shift in the population cohort, and influence the behaviour differences within population cohort, causing a plenty of social problems in the world. Research shown that in Indonesia, social problem is one of the highlight in the society nowadays. Hence, this research is aiming to contribute to a design of a serious game teach social critique to adults, and the evaluations of the serious game design for social problems. The results demonstrate the participants rated that they are happy with the game. Moreover, from the questionnaire, the average score for all items is 3,968, and the highest score belongs to Q6 (4,223), while the lowest score belongs to Q4 (3,800). Moreover, 81% of the players got the right messages about social critique to the society. Finally, the short interview shows the participants felt that the experience when playing the game empower them to get right messages about social critique to the society, where 90% agreed they have gained knowledge and awareness regarding to Narcotics Psychotropic and Addictive Substance and culture of littering arise in the Indonesia. [ABSTRACT FROM AUTHOR]

This paper adopted regression approach with Least Square and Natural Logarithmic transformation in response variables to predict the number of Dengue fever attacks in Malang Regency, Indonesia. The prediction involved weather factors. 8 models were prepared, and it was found that the weather factor was the most influential. Some tests, including hypothesis test, were adopted to identify the significance of the model found. The model using response variable with logarithmic natural transformation resulted better model compared to the ones without transformation. It was also supported by the average MAPE of the model that was less than 10%. Therefore, it was identified that the regression approach will work well if both dependent and independent variables have relatively similar variances so that the variability of the dependent variables can be well explained by the independent variable. [ABSTRACT FROM AUTHOR]

This paper was aimed to understand the antecedents of CAATT adoption by external auditors in public accounting firms. The underlying research model was adapted from Technology Adoption Model (TAM) with the inclusion of external variables. A total of eleven factors were tested as determinants of CAATT’s acceptance. A total of 141 sample data were gathered from various public accounting firms who avidly use CAATT in the greater Jakarta region. The data was then analyzed statistically using Partial Least Square (PLS) Structural Equational Modeling (SEM) techniques. The results provided empirical evidences than CAATT adoption was directly influenced by behavioral intention, perceived usefulness and perceived ease of use. External variables that were deemed as antecedents of perceived usefulness include output quality and result demonstrability. Finally, perceived ease of use was influenced by technological complexity and computer self-efficacy. [ABSTRACT FROM AUTHOR]

Facebook is the most popular social media among teens. In a research conducted by Crowd DNA to 13 countries, two-third of teens aged 13-24 checking on their Facebook 14 times a day. Along with the rising of social media development and popularity, issue of privacy concerns has become public attention. This paper attempted to investigate Facebook users’ information privacy concerns using Internet Users’ Information Privacy Concerns (IUIPC). The data used in this research is collected from a questionnaire survey and analyzed using Structural Equation Modelling (SEM). The result shows that although users are aware with the risk of information loss by using Facebook, it does not have effect on their intention to use Facebook. [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) is still considered a daunting task to solve for us, researcher in this field. Specifically, there is not many research has been done in a local language like Indonesian Language. Nowdays, there are hundreds of systems that require NLP as their main functions. This could be a good opportunity for us to explore this opportunity. This paper contributes models from deep learning training in Indonesian conversation using dual encoder LSTM as well as vector representation models trained with three corpora using Skip-gram method. The results show that the models are able to make a good correlation, synonym from a particular word in the words representation of vector models. In addition, the conversation models resulted in 1.07 of perplexity in the Combined model in the 14000 th steps. [ABSTRACT FROM AUTHOR]

Hierarchical Linear Mixed Model (HLMM) is an extension of Linear Mixed Model with hierarchical levels of observation. HLMM allows researchers to model different types of covariance structure to describe data properly while in classical linear model the covariance structure defines in constant variance and correlation that hardly applicable for longitudinal data. This paper describes two levels HLMM which represents a single growth curves model. Level-1 presents growth shape to capture within-subject effect and level-2 presents growth parameters that characterized between-subject differences. We model the covariance structure of level-1 random effect to excavate individual growth performance and applied to longitudinal data from poverty data of 34 provinces in Indonesia. Different types of covariance structures are modeled using PROC MIXED in SAS system, produce that AR(1) is the alternative of constant covariance structure and ARH(1) as an alternative for non-constant variance structure based on -2RLL, AIC and BIC criteria. [ABSTRACT FROM AUTHOR]

Collaborative consumption has been changing how the people consume products in recent years. The economy model has been adapted by rising Start-Ups and enables lower-income consumers to remove the cost barrier by using access-based consumption. However, up until now the research and empirical study about collaborative consumption practice in a developing country with lower-income consumers compared to developed country is very limited. In this paper, we will explore one of the systems of the collaborative consumption, product-service system in term of customer loyalty by using data from babyloania.com, a Start-Up that using this model. We use multiple regression method with 266 transaction data from customers who have already made at least twice transaction and joined as members for at least 4 months to predict the customer lifetime value and check the significance of its antecedents. In our findings, initial perceived value of saving benefit, initial recency, and initial monetary value have significant effect to customer loyalty measured by transaction frequency and customer lifetime value. [ABSTRACT FROM AUTHOR]

Organizational culture believed as an enabler's of knowledge management implementation. Others assumed that one of critical success factor of knowledge management can be seen from its culture. Generally organizational culture has positive impact to knowledge management. Type of organizational culture can be a guide to encourage the knowledge management (KM) implementation strategy and programs. Culture can direct organization member to behave in certain manners, rules, procedures and policies as an organizational mechanism. This paper describes the process to determine the current organizational culture and suggestion future culture for implement knowledge management in government. OCAI (Organizational Culture Assessment Instrument) and its framework (Competing Value Framework) were used for identifying type of organizational culture in some government ministries/agencies which duties to manage government capital. Result of this study will be used as references for implementing knowledge management for Indonesian Government Human Capital Management for achieve their goals and competitive advantages. [ABSTRACT FROM AUTHOR]

This study aims at testing the conceptual model for predicting intention to use the information system as part of DeLone-Mclean information system success framework. A study literature has revealed that DeLone-Mclean Information System success model has difficulty for defining predictor variables for intention to use. This paper offers a solution by finding the proper variables from technology acceptance models which have strong theoretical background for predicting behavioral intention. A conceptual model is proposed based on literature review. An empirical study is conducted to validate the conceptual model. The object for empirical study is a government agency which has offices in several cities/towns in Indonesia. A quantitative data analysis is being done using SmartPLS with the result showing that perceived usefulness is the strongest predictor for intention to use while service quality surprisingly gives a negative coefficient toward intention to use. [ABSTRACT FROM AUTHOR]