Accurate prediction of food consumption is essential for strengthening regional food security planning, particularly in areas experiencing increasing food demand and environmental uncertainty. This study aims to predict food consumption patterns in Sukabumi Regency, West Java, Indonesia, using an integrated artificial intelligence approach. The research combines the Adaptive Neuro-Fuzzy Inference System (ANFIS) for forecasting food consumption trends with three machine learning classification algorithms—Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR)—to classify food consumption levels. Historical rice consumption data from 2014 to 2024 were used to train the forecasting model and generate projections up to 2030. The ANFIS training process was conducted with 100 epochs and an error tolerance of 0, resulting in a training error value of 0.182, indicating strong model learning capability. The comparison between predicted and actual consumption values showed a prediction accuracy of 95.2%, demonstrating the reliability of the model in capturing consumption patterns. Furthermore, food consumption levels were classified into three categories: low, medium, and high. The classification results revealed that Random Forest achieved the most consistent performance across cross-validation folds, while SVM and Logistic Regression experienced misclassification in the medium consumption category. In several evaluation scenarios, machine learning models achieved accuracy levels up to 99.75%, precision 99.76%, recall 99.75%, and F1-score 99.75%. The integration of ANFIS forecasting and machine learning classification provides a robust analytical framework for understanding food consumption dynamics and supports data-driven policy formulation aimed at strengthening regional food security in Sukabumi Regency.
1 April 2021 in IOP Conference Series: Earth and Environmental Science
This research was conducted to examine the advantages of the application of integrated farming systems between goats and ducks with terubuk in Sukabumi. The research is a case study from the farmers who adjust integrated farming systems then the data was analyzed descriptively qualitative. The result of the study show that the application of this integration between goats and ducks with terubuk has advantages in terms of cultivation, social and economic aspects. Based on the cultivation aspect, this system is efficient because of the continuous availability of feed. Furthermore, based on social aspect can minimize problems such as problem that arise due to presence of waste that cause pollution can be overcome because of the use of waste are more useful. Economic aspect of this system to be efficient because of an increase in income by reducing expenses for feed by 60% and reducing fertilizer requirement by 100%
Food security assessment in disaster-prone areas requires accurate and adaptive approaches capable of capturing dynamic production-consumption relationships. This study aims to develop and evaluate machine learning-based classification models for determining regional food security status using a Food Security Index (FSI), defined as the ratio of local food production to annual consumption requirements with an added safety buffer. Three algorithms were compared: Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). Model performance was evaluated using k-fold cross-validation and assessed through accuracy, precision, recall, F1-score, and confusion matrix analysis. The results show that SVM achieved the highest and most consistent performance, with accuracy ranging from 92% to 96%, precision of 0.93, recall of 0.94, and an F1-score of 0.93. Random Forest demonstrated moderately strong performance (accuracy: 88-92%; F1-score: 0.87), while Logistic Regression exhibited the lowest performance (accuracy: 80-85%; F1-score: 0.80), indicating its limitation in modeling non-linear relationships. Confusion matrix analysis reveals that SVM maintains stable classification across all validation folds with minimal misclassification, whereas errors in all models are predominantly concentrated in regions with FSI values near the classification threshold (FSI ≈ 1), highlighting the challenge of boundary-sensitive cases. Substantively, the integration of production-consumption ratios with buffer reserves in the FSI effectively captures both food availability and system resilience, distinguishing surplus regions (FSI ≥ 1) from structurally vulnerable regions (FSI < 1). These findings confirm that SVM is the most suitable approach for food security classification in disaster-prone areas due to its ability to model non-linear patterns and optimize decision boundaries. This study provides a robust and scalable framework for data-driven food security monitoring and early warning systems. The results support the use of SVM-based classification to enhance the accuracy of vulnerability detection and to improve the targeting of policy interventions in disaster-prone regions.
5 December 2020 in MIMBAR : Jurnal Sosial dan Pembangunan
Problems in agricultural development often encountered in almost all regions in Indonesia are the inadequate use of natural resource potentials, limited ability to manage resources, and lack of synergy between economic actors. These various problems require improved performance through integrated management and development of commodities from upstream to downstream. This research aims to design a working model for the development of local superior commodities in Sukabumi Regency through a survey method conducted in 33 subdistricts. The research resulted in a working model design for the development of local superior commodities in Sukabumi Regency which involved aspects of resource contribution (labor/human resources, natural resources, capital and infrastructure) as well as aspects of work and performance (farmer institutions, extension agencies, financial and marketing institutions, education, training, experiences, sales ability and product demand) to be able to generate advantages. Until now, agricultural development is still facing various obstacles and added value (profitability, market, productivity and learning). All components in the working model design for developing local superior commodities in Sukabumi Regency must be supported by government policies to maximize the increase in added value for both farmers and the community
26 September 2020 in PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
This Community Service is entitled Microgreens Farming Business Training for Housewives in Sukabumi. The empowerment of housewives is intended to produce the potential of housewives, in addition to being able to carry out domestic or domestic duties. Housewives are also able to be active and productive in public activities and economic activities. Microgreens are vegetable seeds that are harvested very young, 7-14 days after germinating and young leaves appear. The method used in this service is the training method; namely, before carrying out direct practice, participants understand through theory first. The training participants were housewives from several women's organizations in Sukabumi. This community service is the acquisition of skills of housewives in farming microgreens and the increasing role of housewives in family welfare through the provision of healthy vegetables for the family.
5 January 2026 in Asian Journal of Agriculture and Rural Development
Coconuts are among Indonesia’s most important plantation commodities, yet copra farmers continue to face low bargaining power, weak institutions, and limited technology adoption. This study assesses the determinants of smallholder productivity and welfare in the copra value chain by integrating supply chain dynamics, market conditions, institutional capacity, and technology adoption. Research was conducted in Lawele Village, Buton Regency, using a mixed-methods design. Primary data were collected from 70 farmers and three collectors through surveys, interviews, and field observations. Analytical methods combined descriptive cost and flow analysis with Partial Least Squares Structural Equation Modeling (PLS-SEM). Results show that supply chain efficiency and market demand significantly influence farmer outcomes only when mediated by institutional strength and technology use. Institutions have the strongest effect on productivity and welfare, while technology adoption enhances quality and competitiveness when supported by stable demand and cooperative governance. These findings empirically support the Structure-Conduct-Performance (SCP) perspective by demonstrating that institutional arrangements and technology adoption function as critical transmission mechanisms between market structure and farmer welfare outcomes. This study also highlights the need for integrated policy interventions that prioritize institutional strengthening, cooperative-managed technology, and transparent market systems. The study suggests that policy implications, which are manifested through empowerment of rural cooperatives, facilitation of digital market access, and expansion of farmer training programs, are essential to enhance smallholder resilience.