Claim Missing Document
Check
Articles

Found 4 Documents
Search

Pengaruh Penggunaan Random Undersampling, Oversampling, dan SMOTE terhadap Kinerja Model Prediksi Penyakit Cardiovascular (CVD) Uswatun Hasanah; Agus Mohamad Soleh; Kusman Sadik
Jurnal Matematika, Statistika dan Komputasi Vol. 21 No. 1 (2024): SEPTEMBER 2024
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v21i1.35552

Abstract

Cardiovascular Disease (CVD) or commonly known as Heart Disease is a leading cause of mortality globally, prompting extensive research into predictive models to assess individual risk and plan preventive measures. Machine learning approaches such as Random Forest, Support Vector Machine (SVM), and LASSO Logistic Regression have showed promise. Recent studies have indicated that traditional resampling methods like Random Oversampling, Random Undersampling, and SMOTE may not significantly improve model discrimination. This study aims to evaluate the impact of these techniques on the performance of Cardiovascular Disease (CVD) prediction models, utilizing data from the UCI Machine Learning Heart Disease database. By employing LASSO Logistic Regression, Random Forest, and Support Vector Machine (SVM) with resampling techniques, including Random Oversampling, Random Undersampling, and SMOTE. This research seeks to enhance understanding of model performance in addressing class imbalances within the dataset and contribute to refining cardiovascular disease (CVD) prediction strategies. This study demonstrates that the use of the SMOTE technique significantly enhances the performance of cardiovascular disease (CVD) prediction models. Specifically, when combined with the Random Forest algorithm, SMOTE achieves the best performance in terms of accuracy, sensitivity, and specificity. This highlights the importance of selecting appropriate resampling techniques to handle class imbalance in datasets. Consequently, this research contributes to refining CVD prediction strategies and provides new insights into improving prediction accuracy in imbalanced medical data.
Effect of Solvent Type on the Antibacterial Activity of Trigona laeviceps Propolis Extract Intan Nurul Azni; Dede Robiatul Adawiyah; Uswatun Hasanah; Nancy Dewi Yuliana
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol. 15 No. 1 (2026): February 2026
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtepl.v15i1.335-345

Abstract

Propolis is a resinous compound which is mixed with saliva, wax, and other metabolic products of bees. One of the benefits of propolis is as an antimicrobial agent. The objective of this research was to determine antibacterial activity Trigona laeviceps bees propolis originating from Bogor West Java extracted with various solvents (water, ethanol, hexane). The tested bacteria consist of 2 Gram negative and 5 Gram positive bacteria. The raw propolis were characterized for gum, tannin, flavonoid, alkaloid, saponin, total phenol content, and proximate composition. Antibacterial activity was tested using the disc diffusion method. The data were analyzed using the ANOVA test and further tested with the Duncan test at a significance level of 5%. The results showed that the largest component of the sampel was lipid (65.47%). Raw propolis contains phenol (3.08 mg/g), tannin (34.45 mg/g), and flavonoid (21.88 mgQCE/g). The highest yield of propolis extract was obtained with hexane solvent (51.03%), followed by ethanol (18.17%), and water (15.58%). All propolis extracts did not have an inhibition zone against Gram-negative bacteria, but did for Gram-positive bacteria. The propolis extract using ethanol showed the highest diameter inhibition zone (16.92 mm). The finding of this study may be utilized to improve Trigona laeviceps propolis quality in Bogor.
Effect of Thawing Process on the Quality of Chicken Thigh Meat Anggita Reizda Siman; Winiati Pudji Rahayu; Uswatun Hasanah
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol. 15 No. 1 (2026): February 2026
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtepl.v15i1.385-395

Abstract

Frozen meat handling, especially during the thawing stage, can affect meat quality and influence the final product. This study aimed to evaluate the effects of thawing method and duration on the quality of frozen and steamed chicken thigh meat. The experiment was arranged in a completely randomized design with two replications. The thawing methods included room temperature (4, 5, 6 h), blast thawing (75, 105, 135 min), and cold temperature (18, 21, 24 h). The observations included drip loss, total plate count (TPC), total free fatty acids (FFA), and soluble protein content. The effect of thawing on steamed meat quality was evaluated for the texture, protein content, fat content, and hedonic scores. The data were statistically analyzed using one-way ANOVA test continued by independent sample t-test. The results showed that thawing duration within the same method did not significantly affect drip loss or TPC, but longer thawing times increased FFA across all methods. Prolonged thawing at room and cold temperature significantly reduced soluble protein content. Thawing at cold temperature for 18 h was the most effective with the lowest drip loss (1.12%) and the highest soluble protein content (34.4 mg/g). Results of steamed meat analysis showed significant differences in texture and fat content between thawed and fresh meat, but no significant differences was observed in protein content or hedonic scores
Verification of Alternative Agar Plate Method for Quantitative Analysis of Yeasts and Molds in Cocoa Products Chairia Faulita Ananti; Uswatun Hasanah; Harsi Dewantari Kusumaningrum
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol. 15 No. 1 (2026): February 2026
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtepl.v15i1.213-222

Abstract

Cocoa beans are vital raw materials in the food industry and are processed into various cocoa products. These products must meet quality and food safety standards, as contamination by yeasts and molds can reduce product quality and shelf life. Conventional microbiological methods often require long incubation times, delaying quality control. This study aimed to verify Symphony Agar as a rapid method for enumerating yeasts and molds in cocoa products following ISO 16140-3:2021 guidelines and to compare it with conventional methods. Verification consisted of two stages: (1) implementation verification, assessing standard deviation of intralaboratory reproducibility (SIR), and (2) food item verification, assessing estimated bias (eBias). Implementation verification on cocoa powder yielded SIR values of 0.121 log₁₀ CFU (pour plate) and 0.171 log₁₀ CFU (spread plat), both below the acceptable threshold, indicating good reproducibility. Food item verification using cocoa powder, cocoa cake, and cocoa liquor showed eBias values under 0.5 log₁₀, meeting the requirements. A comparative study using an independent t-test found no significant difference between Symphony Agar and DG18 Agar. The results indicate that Symphony Agar is suitable as an alternative medium for yeasts and molds analysis in cocoa products, offering the benefit of a shorter incubation time without compromising accuracy.