The global food crisis is perceived to have a significant impact on the national food sector. Time series clustering, a potent data mining technique, is employed to decipher and interpret intricate temporal patterns. Dynamic Time Warping (DTW), a measure that currently appears to be the most relevant, is predicated on the distance between sequences of elements. This paper explores the application of DTW in data mining algorithms to cluster commodity prices in Indonesia, aiming for enhanced accuracy based on time series movement. The clustering algorithm employs the K-Means method, necessitating a comprehensive description of the groups it forms. The analysis results reveal time series clustering for commodity prices using K-Means. Optimal results are achieved with five clusters, based on the commodity price trend. Influencing factors include seasonal variations and government policies related to consumer demand. It is imperative for the government to establish a robust market monitoring system to track commodity price fluctuations in real-time, thereby facilitating the design of effective price stabilization policies. The insights gleaned from this study can guide decision-makers in implementing targeted interventions to stabilize prices, bolster food security, and ensure sustainable economic growth. Doi: 10.28991/HEF-2024-05-03-02 Full Text: PDF

Coronary Heart Disease (CHD) represents a significant public health challenge in Indonesia, contributing substantially to morbidity and mortality rates. We propose a new method for modeling CHD risk by considering the influencing factors, namely age, fatty food consumption and anxiety using Penalized Spline Nonparametric Logistic Regression (PSNLR) approach to analyze the CHD and non-CHD risks affected by these influencing factors. The proposed method gave results a percentage of model classification accuracy of 94.31 % and the value of area under the receiver operating characteristic curve (AUC) of 0.96. This means that the proposed method is a powerful method in modeling the CHD risk and it can effectively identify the nonlinear relationship between influencing factors and CHD incidence. This research supports the achievement of Sustainable Development Goals (SDGs) point 3, especially the target of reducing deaths from non-communicable diseases such as CHD through improving disease prevention and treatment. The use of more accurate models in identifying risk factors also contributes to efforts to improve overall public health and strengthen health care systems.•A cross-sectional survey on influencing factors of CHD risk was conducted at the Airlangga University Hospital.•For analyzing relationship between influencing factors and CHD risk, we used PSNLR method.

Predictive risk modeling for outcomes of ischemic and hemorraghic stroke using feed-forward neural networks

In this study, we develop a regression analysis method, namely, the Semiparametric Binary Logistic Regression (SBLR), by extending the classical logistic regression that integrates both parametric and nonparametric components, which allows it to simultaneously model linear and non-linear relationships. Here, to obtain the estimation of a nonparametric component in the form of a non-linear curve (sigmoid curve), we use the penalized spline, which is a smoothing technique used in the nonparametric approach due to its ability to produce smooth and adaptive curves for fluctuating data. In this smoothing technique, selecting the optimal smoothing parameters plays an important role in fitting the model. Commonly, this selection is based on the minimum value of ordinary Cross-Validation (CV) or Generalized Cross-Validation (GCV). However, these CV and GCV criteria cannot be used when the CV and GCV curves continuously decline and never rise; the minimum CV and GCV values would not be achieved because they are not directly applicable due to the non-quadratic nature of the log-likelihood function. Therefore, a Generalized Approximate Cross-Validation (GACV) criterion is used to address such cases. This distinguishes it from previous studies that used the CV or GCV criterion. In the application to real data, we define an SBLR model of Coronary Heart Disease (CHD) risk factors that can be used for prediction and interpretation purposes. The results of the study successfully demonstrate the efficacy of the proposed method in identifying critical non-linear thresholds for CHD risk factors, and it is statistically valid and highly effective for CHD risk prediction. In the future, we can use the results of this research as a basis of an early warning system, specifically alerting individuals with moderate stress levels and dietary habits exceeding the identified thresholds to be aware of the heightened probability of developing CHD. In addition, this research aligns with point three of the Sustainable Development Goals (SDGs), namely, premature mortality reduction from non-communicable diseases by 2030.

Malaria remained a significant global health issue, particularly in tropical and subtropical regions. The disease resulted in a substantial number of clinical cases and deaths each year, with high-risk groups including infants, toddlers, and pregnant women. Accurate and prompt diagnosis was a key factor in managing the disease. To address this issue, the research aimed to develop an automated system for the classification of Plasmodium falciparum malaria parasites based on blood smear images. The methods employed included image feature selection using Principal Component Analysis (PCA) and the Support Vector Machine (SVM) approach for classification. The research findings indicated that in the image feature selection process, the category of normal malaria exhibited distinctive characteristics with PC1 and PC2 values that tended to be negative and dispersed, whereas the category of parasitic malaria displayed greater variability in both PC1 and PC2 components. Furthermore, the evaluation of the classification system's accuracy using SVM with three different kernel types showed promising results. The average accuracy through K-fold cross-validation for the polyinomial, linear, and radial basis function kernels was 96.7%, 98.9%, and 94.4%, respectively. These results highlighted the significant potential of SVM utilization in the classification of Plasmodium falciparum malaria parasites based on blood smear images.

Diabetes Melitus Tipe 2 (DMT2) merupakan tantangan kesehatan kritis di Indonesia, namun pemodelan faktor risikonya sering terhambat oleh ketidakseimbangan kelas di mana individu sehat melebihi jumlah kasus positif. Penelitian ini memodelkan risiko DMT2 menggunakan pendekatan hybrid yang menggabungkan Synthetic Minority Over-sampling Technique (SMOTE) dan Multivariate Adaptive Regression Splines (MARS). Penelitian ini menggunakan data medis dengan ketidakseimbangan awal 62% sehat dan 38% kasus DMT2. SMOTE diterapkan untuk menyeimbangkan distribusi training, diikuti dengan pemodelan MARS untuk menangkap interaksi non-linear. Hasil penelitian menunjukkan bahwa model SMOTE-MARS secara signifikan mengungguli MARS standar, mencapai Akurasi 0,70 dan AUC 0,73, dibandingkan dengan AUC model standar yang hanya 0,458. Model optimal mengidentifikasi Berat Badan, Tinggi Badan, dan Konsumsi Gula sebagai prediktor utama. Secara spesifik, berat badan di bawah 48 kg teridentifikasi sebagai faktor protektif yang kuat (OR 0,22), sedangkan tinggi badan kurang dari 165 cm (OR 1,22) dan interaksi berat badan berlebih (>62 kg) dengan konsumsi gula (OR 1,12) merupakan faktor risiko signifikan. Tingginya nilai sensitivitas mengindikasikan bahwa model SMOTE-MARS sangat potensial digunakan sebagai instrumen deteksi dini untuk mengidentifikasi pasien yang berisiko tinggi terkena diabetes.