16 results
Search Results
2. Balancing peatlands fire data using ANS-SMOTE method for improvement prediction of peatlands fire occurrence.
- Author
-
Rosadi, Dedi, Arisanty, Deasy, and Andriyani, Widyastuti
- Subjects
- *
PEATLANDS , *MACHINE learning , *FORECASTING - Abstract
It is known that the studies of peatlands fire occurrences in Indonesia are less studied before. In our previous study, the prediction of the peatlands fire occurrence was modeled using various machine learning classification approaches. It is found that using South Kalimantan Province data, in the empirical study we previously found that the datasets are unbalanced, i.e., the occurrence and the nonoccurrence of fire hotspots areas. In the study presented in this paper, to improve the classification performance, we consider Adaptive Neighbor Synthetic Majority Oversampling Technique (ANS-SMOTE) approach to balance the data. Using the considered empirical data, we found that this method did not always gives improvement in the classification results. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Design of a Traceability System for a Coffee Supply Chain Based on Blockchain and Machine Learning.
- Author
-
Ligar, Bonang, Madenda, Sarifuddin, Mardjan, Sutrisno, and Kusuma, Tubagus
- Subjects
- *
COFFEE beans , *BLOCKCHAINS , *CONVOLUTIONAL neural networks , *MACHINE learning , *COFFEE plantations , *SUPPLY chains , *DATA augmentation , *VIRTUAL machine systems - Abstract
Purpose: This paper aims to develop a coffee supply chain traceability system based on Blockchain (BC) and Machine Learning (ML) with the aim of ensuring the quality of coffee beans production. BC functions to ensure supply chain performance, while the ML model ensures product quality. Design/methodology/approach: Smart Contracts will be built on the Ethereum Virtual Machine BC network based on Ethereum. The ML model to identify good and bad green coffee beans will be built using different YOLO algorithms, which will go through training and validation stages, namely using the k-fold cross validation method. The ML model algorithm is based on Convolutional Neural Network (CNN) using YOLOv5m, YOLOv6m and YOLOv7. The best model will be chosen based on the results of cross-validation with test data in the form of coffee image data that the model has never seen (unseen data). The whole process of building the ML model is done on the Google Collab Pro+ Virtual Machine. Findings: YOLOv5m outperformed the other models in both non-augmented and augmented training datasets, highlighting the proficiency of YOLOv5m in managing compact datasets and its resilience in the face of data augmentation, positioning it as a prime selection for quality discernment tasks within the realm of green coffee beans. The smart contracts offer an all-encompassing approach for user management, monitoring product status, and presenting traceability data within the framework of coffee plantation administration. Originality/value: This research contributes to the development of blockchain network as a solution to implement traceability systems along coffee supply chains in Indonesia. Moreover, it shows that while blockchain can ensure the process of production along the coffee supply to follow certain guidelines, machine learning can verify whether the product that was produced by utilizing BC is of high quality/acceptable. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Daily prediction of air quality standard in Makassar city, Indonesia.
- Author
-
Soedjarwo, Moedji, Arifin, Bustanul, Tahir, Andi Mukhtar, Farmasiantoro, Adi, Priyanto, Irwan, and Fauzi, Ahmad
- Subjects
- *
AIR quality standards , *AIR quality indexes , *EMISSION standards , *LONG-term memory , *STANDARD deviations , *AIR quality , *MACHINE learning - Abstract
The air quality index is an important air quality standard for assessing air pollution, wherein to develop spatio-temporal air quality index prediction models in hourly temporal frequencies using ground-based sensor data combined with satellite meteorological and remote sensing data. Applying machine learning method, mainly encoder decoder long short term memory (EDLSTM) as the predictor model, this paper describes daily prediction studies of air quality index (AQI) level and particulate matter (PM)2.5 concentration. In the process, the data preprocessing and exploratory data analysis (EDA) approach was used to mitigate data processing errors by identifying missing values, outliers, and features correlation in the whole dataset. It then was continued by analyzing trends of identified pollutants over time to develop models that produce future predictive outputs. The final work showed that for the AQI standard, EDLSTM model with the root mean squared propagation (RMSProp) optimizer at epoch 50 is the best prediction model since it produced the lowest root mean squared error (RMSE) and mean absolute error (MAE) values, 5.96 and 8.09 sequentially. Meanwhile, the model with Adam optimizer at epoch 700 is the best prediction for PM2.5 concentration standard, in which the RMSE and MAE delivered the lowest values, 2.53 and 3.53. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
5. Machine learning and data augmentation in the proxy means test for poverty targeting.
- Author
-
Wobcke, Wayne and Mariyah, Siti
- Subjects
- *
DATA augmentation , *STATISTICAL learning , *POVERTY , *MACHINE learning , *DATA science , *SUSTAINABLE development - Abstract
Recent years have seen increased interest in the use of alternative data sources in the definition and production of official statistics and indicators for the UN Sustainable Development Goals. In this paper, we consider the application of data science to the production of official statistics, illustrating our perspective through the use of poverty targeting as an application. We show that machine learning can play a central role in the generation of official statistics, combining a variety of types of data (survey, administrative and alternative). We focus on the problem of poverty targeting using the Proxy Means Test in Indonesia, comparing a number of existing statistical and machine learning methods, then introducing new approaches in the spirit of small area estimation that utilize area-level features and data augmentation at the subdistrict level to develop more refined models at the district level, evaluating the methods on three districts in Indonesia on the problem of estimating 2020 per capita household expenditure using data from 2016–2019. The best performing method, XGBoost, is able to reduce inclusion/exclusion errors on the problem of identifying the poorest 40% of the population in comparison to the commonly used Ridge Regression method by between 4.5% and 13.9% in the districts studied. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
6. Machine learning application for news classification in measuring Indonesian democracy index.
- Author
-
Arsyi, Farhan Anshari and Pramana, Setia
- Subjects
- *
MACHINE learning , *DEMOCRACY , *ELECTRONIC newspapers - Abstract
The Indonesian Democracy Index (IDI) is an assessment of the condition of democracy in every province in Indonesia. The IDI calculation is carried out by collecting democracy events that occur in every province in Indonesia through news in newspapers and official state documents. Events that have been collected are reviewed and classified into 1 of 28 IDI indicators, then verified through Focus Group Discussions (FGD) and in-depth interviews with related parties. After that, IDI calculated by counting the events that occur by indicators in every province. So far, the process of classifying democracy events is still done manually by officers using news in newspapers as data source. Machine learning, especially text classification, gives us the opportunity to use it in automating the classification of democracy events. Big data opens up opportunities for alternative data sources that are abundant, available at any time, and easy to obtain. This paper will be focused on democracy events collection and classification task, we will examine the application of Machine Learning for classifying democracy events into IDI variables and indicators with online news as the data source and implementing it into a system of collecting, classifying, and managing democracy events. The results showed that Machine Learning was able to classify democracy events quite well into IDI variables and indicators. Moreover, the system built could run as expected. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
7. Agriculture information system for horticulture based on machine learning.
- Author
-
Sumarudin, A., Puspaningrum, Alifia, Suheryadi, Adi, and Yamani, Harsa
- Subjects
- *
MACHINE learning , *INFORMATION storage & retrieval systems , *WEB-based user interfaces , *INDONESIANS , *AGRICULTURE - Abstract
Agriculture is one of the important sectors in Indonesia. There are several commodities consumed by Indonesian citizens, one of them is shallots as a cooking spice and herbal medicine. Several problems occasionally arise in the shallots cultivation process; one of them is increasing plant pest organism's attacks. However, the control process is still done conventionally. Therefore, it is necessary to build a system to diagnose diseases automatically. This paper proposes an information system for agriculture shallots based on machine learning using dempster Shafer. After collecting the data, dempster Shafer is applied to determine and define a reasonable level of confidence and a function to evaluate a possibility. Based on the experiment, the accuracyofmax belief for detection of shallots disease is 60%. By using several scenarios, the experimental result shows that dempster Shafer can detect shallot disease well. Furthermore, the algorithm can be implemented in web and mobile applications based to monitor the controlling process easier. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
8. Predicting the number of Covid-19 cases in Surabaya using hybrid extreme machine learning with particle swarm optimization.
- Author
-
Tuloli, Mohamad Handri, Anam, Syaiful, and Shofianah, Nur
- Subjects
- *
COVID-19 pandemic , *PARTICLE swarm optimization , *MACHINE learning , *HIGH speed trains , *DISEASE outbreaks - Abstract
Covid-19 has spread to various countries in the world, including Indonesia. Surabaya becomes one of the big cities in Indonesia where the spread of Covid-19 is very fast, so the number of positive cases of Covid-19 is very large and more than 1000 people die because of this disease until November 2020. Prediction of the number of positive cases of Covid-19 can be used to regulate the availability of facilities in hospitals and make plans and policies to overcome this disease outbreak. Many prediction methods have been found, one of which is the Extreme Learning Machine (ELM). ELM has high training speed and accuracy. However, the performance of ELM depends on the number of neurons. When the number of neurons is not precisely determined, the accuracy of prediction becomes worst. Particle Swarm Optimization (PSO) is used to decide the number of neurons. For this reason, this paper proposes a prediction of the Covid-19 cases in the City of Surabaya using the hybrid of ELM and PSO (ELM-PSO). The experiments show that the comparative performance of the proposed methods with several activation functions in the prediction of the Covid-19 cases in the City of Surabaya. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
9. Decarbonization of Indonesia's economy: An analysis using machine learning method.
- Author
-
Sugiawan, Yogi, Putri, Megawati Suharsono, Kaliwanto, Budi, and Sutarto, Falconi Margono
- Subjects
- *
CARBON dioxide mitigation , *PANEL analysis , *ENERGY consumption , *CARBON dioxide , *ECONOMIC expansion , *MACHINE learning , *VECTOR error-correction models - Abstract
A strong correlation between economic growth, energy consumption and carbon dioxide (CO2) emissions has made the increasing level of CO2 emissions becomes a perpetual problem worldwide. Therefore, the efficacy of current energy and environment related policies needs to be evaluated. In this regard, finding a reliable model to accurately forecast CO2 emissions is of importance, particularly for a developing country like Indonesia. By involving an unbalanced panel data of 77 countries covering the period of 1966 to 2019, this paper proposes a model which relies on the machine learning method to forecast CO2 emissions in Indonesia and to predict the feasibility for decoupling CO2 emissions from economic growth. This study finds the beneficial impacts of new and renewable energy on reducing CO2 emissions. However, the peak of CO2 emissions in Indonesia was not predicted. Hence, decarbonization of Indonesia's economy is not likely to be achieved in the near future. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Automated Multi-Label Classification on Fertilizer-Themed Patent Documents in Indonesia.
- Author
-
Yaman, Aris, Sartono, Bagus, Soleh, Agus M., Indrawati, Ariani, and Kartika, Yulia Aris
- Subjects
- *
PATENTS , *K-nearest neighbor classification , *MACHINE learning , *CLASSIFICATION - Abstract
Patent literature research has a high scientific value for the industrial, commercial, legal, and policymaking communities. Therefore, patent analysis has become crucial. Patent topic classification is an important process in patent topic modeling analysis. However, the classification process is time-consuming and expensive, as it is usually carried out manually by an expert. Moreover, a patent document may be categorised in more than one category or label, further complicating the task. As the number of patent documents submitted increases, creating an automated patent classification system that yields accurate results becomes increasingly critical. Therefore, in this paper, we analyse the performance of two algorithms with regard to multi-label classification in patent documents: multi-label k-nearest neighbor (ML-KNN) and classifier chain k-nearest neighbor (CC-KNN), combined with latent Dirichlet allocation (LDA). These two methods have a considerable advantage in handling the continuously updated dataset; they also exhibit superior performance compared to other multi-label learning algorithms. This study also compares these two algorithms with the term frequency (TF)-weighting measure. The optimal value obtained is based on the following evaluation parameters: micro F1, accuracy, Hamming loss, and one error. The result shows that the ML-KNN method is better than the CC-KNN method and that the multi-label classification based on topics (patent LDA) is better than the TF-weighting technique. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. Random Forest for Breast Cancer Prediction.
- Author
-
Octaviani, T. L. and Rustam, Z.
- Subjects
- *
BREAST cancer , *BREAST cancer prognosis , *BIG data - Abstract
One of cancer that commonly causes most of the death is breast cancer. According to WHO data published in 2017, breast cancer deaths in Indonesia reached 21,287 or 1.27 % of total deaths. Delay in knowing of the condition of breast cancer in women with breast cancer, results in increased mortality, poor prognosis, and decreased survival rates, which are also associated with lower awareness of breast cancer, and also recommended non-adherence to screening. In this paper, we propose a random forest for breast cancer prediction. Random forest is one of many classification techniques, and it is an algorithm for big data classification. Random forest classification is applied to cancer microarray data to achieve a more accurate and reliable classification performance. The accuracy in this paper is 100 %. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
12. Estimating heterogeneous policy impacts using causal machine learning: a case study of health insurance reform in Indonesia.
- Author
-
Kreif, Noemi, DiazOrdaz, Karla, Moreno-Serra, Rodrigo, Mirelman, Andrew, Hidayat, Taufik, and Suhrcke, Marc
- Subjects
- *
HEALTH insurance statistics , *HEALTH policy , *MATERNAL health services , *MOTHERS , *POLICY analysis , *RURAL conditions , *MACHINE learning , *WOMEN , *RANDOM forest algorithms , *POPULATION geography , *HEALTH care reform , *SOCIOECONOMIC factors , *POOR people , *INFANT mortality , *POVERTY , *ALGORITHMS , *RURAL population - Abstract
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]
- Published
- 2022
- Full Text
- View/download PDF
13. An Improved Method of Clay-Induced Rock Typing Derived from Log Data in Modelling Low Salinity Water Injection: A Case Study on an Oil Field in Indonesia.
- Author
-
Zakyan, Hafizh, Permadi, Asep Kurnia, Pratama, Egi Adrian, and Naufaliansyah, Muhammad Arif
- Subjects
- *
OIL field flooding , *OIL fields , *DATA logging , *ARTIFICIAL neural networks , *DATA modeling , *CLAY minerals - Abstract
Low salinity water injection (LSWI) is an emerging way to improve waterflood performance through chemical processes. The presence of clay minerals is one of the required parameters to successfully implement LSWI in sandstone formations. The ability of clays to exchange the cations, represented by cation exchange capacity (CEC), leads to oil detachment from the rock surface and changes the formation wettability toward water-wet. There are still limited studies that discuss the implementation of specific CEC models in the field-scale LSWI reservoir simulation. This paper attempts to propose an improved method of clay-induced rock typing that can be representatively implemented for field-scale reservoir simulation. The scope of this study is limited to a sandstone reservoir from an oil field in Indonesia. The oil is considered light, and the reservoir contains main clay minerals, including kaolinite and illite, and a trace of chlorite was also found from the XRD evaluation. CEC can be derived from log data, while rock type can also be estimated from log data by using the artificial neural network method. The main finding is that the combination of those variables, i.e., log data, rock properties, and CEC, results in an improved method to characterize and classify the clay into three types associated with conventional rock types. The classification obtained by the clay typing method can be utilized as an input for advanced LSWI modeling, which is expected to provide more robust results. Furthermore, dispersed clay has a strong influence on the magnitude of cation exchange capacity rather than laminar and structural clays. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
14. New recommendation to predict export value using big data and machine learning technique.
- Author
-
Nooraeni, Rani, Nickelson, Jimmy, Rahmadian, Eko, and Yudho, Nugroho Puspito
- Subjects
- *
BIG data , *GENETIC algorithms , *ARTIFICIAL neural networks , *MACHINE learning - Abstract
Official statistics on monthly export values have a publicity lag between the current period and the published publication. None of the previous researchers estimated the value of exports for the monthly period. This circumstance is due to limitations in obtaining supporting data that can predict the criteria for the current export value of goods. AIS data is one type of big data that can provide solutions in producing the latest indicators to forecast export values. Statistical Methods and Conventional Machine Learning are implemented as forecasting methods. Seasonal ARIMA and Artificial Neural Network (ANN) methods are both used in research to forecast the value of Indonesia's exports. However, ANN has a weakness that requires high computational costs to obtain optimal parameters. Genetic Algorithm (GA) is effective in increasing ANN accuracy. Based on these backgrounds, this paper aims to develop and select an AIS indicator to predict the monthly export value in Indonesia and optimize ANN performance by combining the ANN algorithm with the genetic algorithm (GA-ANN). The research successfully established five indicators that can be used as predictors in the forecasting model. According to the model evaluation results, the genetic algorithm has succeeded in improving the performance of the ANN model as indicated by the resulting RMSE GA-ANN value, which is smaller than the RMSE of the ANN model. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
15. Wavelet Based Machine Learning Approach for Spectral Seismic Signal Analysis: A Case Study North Tapanuli Earthquake.
- Author
-
Sinambela, Marzuki, Tarigan, Kerista, Humaidi, Syahrul, and Situmorang, Marhaposan
- Subjects
- *
EARTHQUAKE resistant design , *MACHINE learning , *SEISMIC networks , *CASE studies , *WAVELET transforms , *EARTHQUAKES - Abstract
Machine Learning of seismic signals is considered to automatize the analysis of years of the recorded signal. In this research, we considered using the wavelet transform based machine learning approach to analysis the spectrum signal which recorded from Broadband Seismic Network in North Tapanuli area. We use the signal seismic which recorded from GSI, MNSI, PBSI, PSI, SBSI, and TDNI which has been deployed in North Tapanuli, North Sumatera, Indonesia. The main aim of this paper to extract the different the value and spectrum of the seismic signal and identify the energy of signal of seismic which recorded from the sensor. The result shows that for all signal, which recorded form broadband seismic network information for detection and characterization is found in the instantaneous spectrum, and the makes seismic signal most useful is that this spectrum changes over time. The wavelet-based machine learning approach utilizing a complex Morlet analyzing wavelet is not only particularly suitable to clearly and simultaneously of seismic signals but also powerful for processing frequency-energy with variant signal seismic with a short period. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
16. Mapping of rice growth phases and bare land using Landsat-8 OLI with machine learning.
- Author
-
Ramadhani, Fadhlullah, Pullanagari, Reddy, Kereszturi, Gabor, and Procter, Jonathan
- Subjects
- *
RICE , *MACHINE learning , *ARTIFICIAL neural networks , *SUPPORT vector machines , *LAND use , *KERNEL functions - Abstract
Regular monitoring and mapping of rice (Oryza Sativa) growth phases are essential for industry stakeholders to ensure food production is on track and to assess the impact of climate change on rice production. In Indonesia, high-cost field surveys have been widely used to monitor the rice growth phases. Alternatively, this research proposes a methodology to retrieve multi-temporal rice phenology (vegetative, reproductive, and ripening) and bare land mapping using medium resolution remote sensing imagery obtained from Landsat-8 Operational Land Imager (OLI) combined with machine learning techniques. In this study, we have used extensive ground validation information collected from 2014 to 2016 for training the models. This ground validation information was obtained from pre-installed webcams across Indonesia. Five different machine learning algorithms were used including random forest (RF), support vector machine (SVM) with three kernel functions (linear, polynomial, and radial) and artificial neural networks (ANN) to classify rice growth phases and bare land. This paper also evaluates the temporal evolution of rice phenology and bare land to check the prediction model consistency between two consecutive dates in 3 years. The results show that the nonlinear SVM algorithm gives the best model accuracy (70.5% with Kappa: 0.66) based on the test dataset and the lowest temporal changes (<11%). Spatial-temporal assessment of rice phenology and bare land from Landsat-8 indicated that the models were reliable and robust over different seasons and years. The distribution of rice phenology maps will enable Indonesian management authorities to supply fertilizer, allocate water resources, harvesting, and marketing facilities more efficiently. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.