Neng Elmi Salehah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Neng Elmi Salehah has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Endang Tri Astutiningsih
Universitas Muhammadiyah Sukabumi, Indonesia
2 shared publications - Mai Fernando Nainggolan
Universitas Santo Thomas, Indonesia
2 shared publications - Reny Sukmawani
Universitas Muhammadiyah Sukabumi
2 shared publications - Sri Ayu Andayani
Universitas Majalengka, Indonesia
2 shared publications - Aulia Miftahunnisa Exa Putriyana
Vaksindo Satwa Nusantara
1 shared publication - Ema Hilma Meilani
Universitas Muhammadiyah Sukabumi
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by FapUNIFESP (SciELO) in Brazilian Journal of Biology
- Vol. 86, e305154
Classification of food security status in disaster-prone areas: a comparative analysis of machine learning models using Support Vector Machine, Random Forest, and Logistic Regression
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.
- 1 January 2026
- Published by FapUNIFESP (SciELO) in Brazilian Journal of Biology
- Vol. 86, e305154
Open AccessClassification of food security status in disaster-prone areas: a comparative analysis of machine learning models using Support Vector Machine, Random Forest, and Logistic Regression
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.
- Open Access
- 30 December 2024
- Published by Institute of Eastern European Research and Consulting in Journal of Innovations and Sustainability
- Vol. 8 (4) , 10
Optimising cattle body weight with terubuk waste feed for sustainable agriculture
Purpose. This research aimed to predict the increase in cow weight through the use of terubuk (Saccharum edule Hassk) waste feed technology based on pH content, silage water content (KA), silage dry weight (BK), and silage fermentation value (NF) on daily increase in cow weight. Results. The results showed that an optimal increase in cow weight by using terubuk waste silage is achievable when silage formula is at pH value of 4.15, KA 74.1, BK 36.6, NF 85.4, and protein 11.2. The values produced the most optimum weight increase during daily observations, namely 1.03 kg/day. These results show that the use of feed technology through terubuk waste silage as an alternative feed based on predictions proved to be very effective in increasing cow weight. Consequently, the development of cow farming businesses could be more efficient based on predictions of weight increase based on input variables contained in waste silage used as feed. The feasibility of implementing innovations in the field of using terubuk waste as an alternative feed is substantiated. Scientific novelty. Utilising terubuk waste feed technology as an alternative feed processed into silage, is a new sustainable solution in the livestock industry. A prediction model for increasing cow weight based on the content of crushed waste silage was created. Other scientific values obtained also show that based on predictions through its utilisation, it can increase production efficiency in the era of sustainable agricultural systems. Practical value. Increasing optimal cattle weight is a goal that every farmer wants to achieve in running their livestock business. Use of terubuk waste as feed can be an alternative solution in overcoming the problem of food scarcity and increasing production efficiency in the era of sustainable agricultural systems.
- 30 December 2024
- Published by Institute of Eastern European Research and Consulting in Journal of Innovations and Sustainability
- Vol. 8 (4) , 10
Open AccessOptimising cattle body weight with terubuk waste feed for sustainable agriculture
Purpose. This research aimed to predict the increase in cow weight through the use of terubuk (Saccharum edule Hassk) waste feed technology based on pH content, silage water content (KA), silage dry weight (BK), and silage fermentation value (NF) on daily increase in cow weight. Results. The results showed that an optimal increase in cow weight by using terubuk waste silage is achievable when silage formula is at pH value of 4.15, KA 74.1, BK 36.6, NF 85.4, and protein 11.2. The values produced the most optimum weight increase during daily observations, namely 1.03 kg/day. These results show that the use of feed technology through terubuk waste silage as an alternative feed based on predictions proved to be very effective in increasing cow weight. Consequently, the development of cow farming businesses could be more efficient based on predictions of weight increase based on input variables contained in waste silage used as feed. The feasibility of implementing innovations in the field of using terubuk waste as an alternative feed is substantiated. Scientific novelty. Utilising terubuk waste feed technology as an alternative feed processed into silage, is a new sustainable solution in the livestock industry. A prediction model for increasing cow weight based on the content of crushed waste silage was created. Other scientific values obtained also show that based on predictions through its utilisation, it can increase production efficiency in the era of sustainable agricultural systems. Practical value. Increasing optimal cattle weight is a goal that every farmer wants to achieve in running their livestock business. Use of terubuk waste as feed can be an alternative solution in overcoming the problem of food scarcity and increasing production efficiency in the era of sustainable agricultural systems.