Abstract:ANNs have the ability to learn from data and recognize unstructured patterns. In face detection, ANNs can be used to recognize faces from images or videos. However, selecting the right ANN method is crucial for achieving…
optimal face detection performance. The results of this study are the highest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images with a comparison of the Learning Vector Quantization method is 96.25% (detection error = 0) with a classification architecture of the test data comparison - training data 70: 30, 20,000 iterations, calculation error tolerance 0.00001 and the number of hidden layer neurons = 5 while the lowest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images based on LVQ features is 85.42% (detection error = 34) with a classification architecture of the test data comparison - training data 70: 30, 10,000 iterations, calculation error tolerance 0.01 and the number of hidden layer neurons = 15
Abstract:Student mental health disorders have become an increasingly important issue due to their significant impact on academic performance and psychological well-being. Machine learning-based approaches offer a promising alternative…
ative for supporting early detection; however, only a limited number of studies have conducted comprehensive evaluations of various ensemble learning algorithms by simultaneously considering predictive performance, computational efficiency, and statistical significance. This study aims to compare ten classification algorithms, namely Random Forest, Extra Trees, Gradient Boosting, Hist Gradient Boosting, AdaBoost, XGBoost, LightGBM, CatBoost, Logistic Regression, and Stacking Ensemble, using 5-fold Stratified Cross-Validation. Model performance was evaluated using Accuracy, Precision, Recall, F1-Score, Receiver Operating Characteristic–Area Under the Curve (ROC-AUC), training time, inference time, confusion matrix, feature importance, as well as One-Way Analysis of Variance (ANOVA) and post-hoc Tukey’s Honestly Significant Difference (Tukey HSD) tests. The experimental results show that CatBoost achieved the highest classification performance, with an Accuracy of 84.86%, an F1-Score of 87.19%, a Recall of 88.03%, and an ROC-AUC of 0.9220. XGBoost delivered comparable predictive performance with a substantially shorter training time (3.92 seconds), while LightGBM was the most computationally efficient algorithm, requiring an average training time of only 0.85 seconds. In contrast, the Stacking Ensemble required the longest training time (215.41 seconds) without providing a statistically meaningful performance improvement over the boosting-based models. The ANOVA results revealed significant differences in ROC-AUC among the evaluated models (p < 0.001), whereas the Tukey HSD test indicated that most boosting algorithms did not differ significantly from one another. These findings provide practical guidance for selecting classification algorithms by balancing predictive performance and computational efficiency to support early mental health screening systems for university students.
Abstract:Iron deficiency anemia remains a nutritional problem among adolescent girls, making the development of acceptable local food products rich in iron important. This study aimed to evaluate the effect of Moringa oleifera leaf…
af flour substitution on the organoleptic characteristics, iron content, and proximate composition of dange cake and to determine the best formulation. An experimental study using a Completely Randomized Design (CRD) was conducted with four formulations: F1 (0 g), F2 (12 g), F3 (25 g), and F4 (37 g) Moringa leaf flour. Organoleptic testing used a 1–5 hedonic scale involving 30 untrained adolescent-girl panelists. Data were analyzed using the Kruskal–Wallis test because the organoleptic data were not normally distributed. The results showed no significant differences in color (p=0.543), aroma (p=0.067), or texture (p=0.085), whereas taste differed significantly (p<0.001). F2 had the highest mean rank for color (67.10), aroma (70.73), taste (82.27), and texture (68.70), and was therefore selected as the best formulation. Laboratory analysis of F2 showed protein 5.16%, fat 4.04%, carbohydrate 63.35%, moisture 23.75%, ash 1.70%, crude fiber 4.65%, and iron 17.10 mg/g as reported in the research results. The findings indicate that dange cake with 12 g Moringa leaf flour substitution has good sensory acceptance and potential to be developed as an iron-rich snack to support anemia prevention among adolescent girls.
Abstract:Financial technology integration can influence unemployment rates in various ways, such as expanding access to the labor market through online platforms, creating new jobs within the financial technology sector itself, or…
r increasing labor market efficiency through technologies such as job matching platforms. Macroprudential policy refers to the steps taken by financial authorities to manage systemic risks in the financial sector. In the context of the Phillips curve, these policies can have a direct or indirect effect on the unemployment rate through their influence on financial system stability and economic growth. In relation to ASEAN countries with the highest unemployment rates, testing this model will pay attention to structural, demographic and economic differences between these countries. These factors will influence how financial technology and macroprudential policy interact with the unemployment rate in each country. The results of this test provide valuable insights for policymakers in ASEAN countries with high unemployment rates. They can use this information to design more effective policies in promoting economic growth and reducing unemployment rates through the appropriate application of financial technology and macroprudential policies.
Abstract:This study aims to understand public interest and awareness of the circular economy in Indonesia by analyzing Google Trends search volumes for keywords over the past five years, from 2017 to 2022: "Waste Recycling," "Circular…
cular Economy," "Waste Management," and "Waste Reduction." Data analysis shows that "Waste Recycling" consistently has the highest and most stable search volume, especially in regions such as South Sulawesi, North Kalimantan, and West Sulawesi, indicating successful local campaigns. In contrast, "Circular Economy" has significantly lower search volumes, even in metropolitan areas, suggesting that this concept is relatively new. Interest in "Waste Management" varies, with higher volumes in South East Sulawesi, East Nusa Tenggara, and Central Sulawesi, highlighting the importance of waste management but also the need for better policy and infrastructure support. "Waste Reduction" has the lowest search volume, indicating the need for intensive educational efforts. Geographical analysis shows significant regional differences, with high-interest areas serving as education centers and low-interest areas needing targeted interventions. This study underscores the necessity for robust educational campaigns, supportive policies, and stakeholder collaboration to enhance the adoption of circular economy practices. These insights inform policy development and the design of effective educational campaigns for environmental sustainability in Indonesia
Abstract:This study aims to determine the financial performance of property and real estate companies in the LQ45 index for the 2017-2021 period listed on the Indonesia Stock Exchange using the Du Pont System approach. Du Pont System…
stem is an analysis that unites activity ratios with profitability constellations to show how these two factors relate in determining return on investment, namely the profitability of company assets. This research is analyzed using qualitative descriptive analysis techniques by analyzing financial statements using the Du Pont System approach that has been published on the Indonesia Stock Exchange which describes real circumstances or events in the company. The data collection techniques used in this study are documentation techniques and literature studies. The results showed that the financial performance of PT Pakuwon Jati Tbk had the highest ROI of 8.38% while PT PP Properti Tbk with the lowest ROI rate of 4.37%, PT Pakuwon Jati Tbk became the company with the best corporate financial performance when compared to other property and real estate companies for the 2017-2021 period.
Abstract:The assessment of student career readiness requires a systematic approach that considers multiple competencies and experiences relevant to workplace demands. This study develops an intelligent decision support system based…
ed on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to evaluate and map student career readiness. The study uses 20 student samples and five assessment criteria: field-specific competence (C1), internship experience (C2), communication skills (C3), digital literacy (C4), and English language proficiency (C5). Each criterion is assigned a weight based on its relative importance. The TOPSIS method involves decision matrix construction, normalization, weighted normalization, determination of positive and negative ideal solutions, distance calculation, and preference value calculation. The results show that Y11 achieved the highest preference value of 0.8296, followed by Y6 (0.7951), Y19 (0.7274), Y5 (0.7116), and Y2 (0.6999), while Y9 obtained the lowest preference value of 0.3112. Based on the classification results, 1 student (5%) was categorized as Highly Ready, 5 students (25%) as Ready, 12 students (60%) as Moderately Ready, and 2 students (10%) as Not Ready. These findings demonstrate that TOPSIS can effectively rank and classify student career readiness based on multiple assessment criteria. The proposed system can support higher education institutions in identifying students’ readiness levels and developing more objective, targeted, and data-driven career development strategies.
Abstract:Village infrastructure development planning often faces challenges in determining priorities due to limited budget allocations and assessment mechanisms that still tend to be subjective. This study aims to build an objective,…
tive, transparent, and measurable Decision Support System (DSS) to determine the priority order of infrastructure development proposals in Asam Jawa Village, Torgamba District. The applied solution integrates the Rank Order Centroid (ROC) method to calculate criteria weighting based on relative importance, and the Simple Additive Weighting (SAW) method to process the alternative ranking calculation. The evaluation was conducted on 23 physical infrastructure proposals using four main criteria: urgency level (C1), physical condition (C2), benefits (C3), and population size (C4). The results indicate that alternative A4 (Construction of Borehole Well and Public Toilet at Field) and alternative A18 (Sejahtera Street Concrete Cast) achieved the highest preference score of 1.000000, followed by other infrastructure proposals in a structured manner. The combined use of ROC and SAW methods is proven to be effective and consistent in generating accurate rural development priority rankings. The integration of these two methods facilitates village government officials in making accountable decisions while minimizing cognitive bias risks in optimizing development budget allocation.
Abstract:Steamed sponge cake (bolu kukus) is a widely consumed traditional snack in Indonesia; however, its reliance on refined wheat flour limits its micronutrient and dietary fiber density. Incorporating composite flours from indigenous…
ndigenous crops, such as tropical pumpkin (Cucurbita moschata) and green pea (Vigna radiata L.), offers a promising strategy for nutritional fortification and dietary diversification. This study aimed to evaluate the proximate composition, sensory acceptability, statistical differences, and production cost feasibility of steamed sponge cakes formulated with varying proportions of pumpkin and green pea flours as partial replacements for refined wheat flour. An experimental design was applied using three formulations: AF09 (Control: 100% wheat flour), BW91 (10% pumpkin flour, 20% green pea flour), and CB88 (15% pumpkin flour, 15% green pea flour). Proximate testing measured moisture, ash, protein, fat, crude fiber, and total carbohydrates (by difference). Sensory acceptance (color, aroma, taste, and texture) was evaluated by 50 semi-trained panelists using a hedonic scale. Data were analyzed non-parametrically using Kolmogorov-Smirnov, Kruskal-Wallis, and post-hoc Mann-Whitney tests. All formulations complied with the Indonesian National Standard (SNI 01-3840-1995) for moisture (31.69%–33.74%), total ash (0.66%–1.05%), crude protein (5.80%–6.65%), and crude fat (1.64%–2.82%). Formula CB88 achieved the highest crude fiber content (0.69%) and lower total energy density (269.88 kcal/100 g). Kruskal-Wallis testing indicated statistically significant differences (p<0.05) among formulations for color, taste, and texture, while aroma exhibited no significant variation (p=0.672). Formula CB88 emerged as the optimal treatment, receiving superior sensory acceptance ratings for color (90% liked) and crumb softness (88% liked) driven by natural β-carotene and pectin-moisture gelation. Production cost analysis demonstrated high economic feasibility for CB88 at IDR 3,374 per 55 g serving. Partial substitution with 15% pumpkin flour and 15% green pea flour (Formula CB88) yields a nutrient-dense, fiber-enriched, and cost-effective functional snack suitable for targeted school nutrition and dietary diversification programs.
Abstract:Pemilihan Ketua Badan Eksekutif Mahasiswa (BEM) merupakan proses penting dalam menentukan mahasiswa yang memiliki kompetensi terbaik untuk memimpin organisasi kemahasiswaan. Namun, proses seleksi yang masih bergantung pada…
da popularitas dan penilaian subjektif berpotensi menghasilkan keputusan yang kurang optimal. Penelitian ini bertujuan membangun Sistem Pendukung Keputusan (SPK) menggunakan metode Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) untuk membantu proses pemilihan Ketua BEM secara objektif. Data penelitian diperoleh melalui wawancara dengan pembina BEM untuk menentukan kriteria dan bobot penilaian. Lima kriteria yang digunakan meliputi kepemimpinan, kemampuan komunikasi, pengalaman organisasi, integritas, dan indeks prestasi kumulatif (IPK). Tahapan metode MOORA terdiri atas penyusunan matriks keputusan, normalisasi, perhitungan nilai optimasi, dan proses perangkingan. Hasil penelitian menunjukkan bahwa alternatif K1 memperoleh nilai optimasi tertinggi sebesar 0,473 sehingga direkomendasikan sebagai Ketua BEM terpilih. Penerapan metode MOORA mampu menghasilkan proses pengambilan keputusan yang lebih objektif, sistematis, transparan, dan akurat sehingga dapat dijadikan sebagai alat bantu dalam menentukan Ketua BEM berdasarkan kriteria yang telah ditetapkan.
The selection of the Student Executive Board (BEM) President is an important process in determining the most qualified student to lead the student organization. However, conventional selection processes often rely on popularity and subjective judgments, which may lead to less optimal decisions. This study aims to develop a Decision Support System (DSS) using the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) method to support a more objective selection process. Research data were collected through interviews with BEM advisors to determine the assessment criteria and their corresponding weights. Five criteria were used, namely leadership, communication skills, organizational experience, integrity, and grade point average (GPA). The MOORA method consists of decision matrix construction, normalization, optimization value calculation, and ranking. The results indicate that candidate K1 achieved the highest optimization value of 0.473 and was therefore recommended as the selected BEM President. The implementation of the MOORA method provides a more objective, systematic, transparent, and accurate decision-making process, making it an effective tool for supporting the selection of the most suitable BEM President based on predetermined criteria.