Search

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]

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]

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]

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]

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]

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]

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]