Stunting is still considered a serious problem and has become a focus of government attention in the national research priorities for 2020-2024, with a stunting prevalence of 21.6% in 2022. The city of Samarinda ranked second highest after the Kutai Kartanegara district in East Kalimantan Province in 2022, with a percentage of 25.3%. Based on previous data mining research trends, the use of classification methods such as KNN, Naïve Bayes, Random Forest, Neural Network, CART, and SVM has generally produced quite high accuracy but still focuses on low-dimensional data, which can lead to significant information loss, potential overfitting, and difficulty in interpretation. Whereas in research topics related to high-dimensional stunting data, the majority still yield low accuracy. This is further supported by the still prevalent class imbalance found in other studies, which can affect the accuracy and recall values of the built model's performance. The objective of this research is to apply the Support Vector Machine (SVM) algorithm with Chi-Square feature selection and the Synthetic Minority Over-sampling Technique (SMOTE) to address high-dimensional stunting data and handle class imbalance. The dataset for this research is sourced from the Samarinda City Health Office, consisting of 26 community health centers with 20 attributes and 102,534 records. The division of training and testing data uses the k-fold cross-validation technique with k=10. The research results show the model's performance is very good, with an accuracy of 96.6%, supported by precision, recall, and f1-score values of 97% each.
In late 2015, the Mount Jailolo complex was shaken by a prolonged earthquake swarm. Mount Jailolo is an ancient volcano that has shown no activity since 1600. The occurrence of an earthquake swarm in the region has sparked speculation about a resurgence of volcanic activity at this ancient volcano. To study the swarm phenomenon in Jailolo, a local scale high-resolution seismic tomography study with a nonlinear approach was conducted beneath the Mount Jailolo complex —a first of its kind. The primary objective of this study is to image the P- and S-wave velocity structures in the upper crust down to a depth of 15 km in 3D for the Mount Jailolo complex (0.8°–1.3° N; 127.2°–127.9° E). Using data from 524 microearthquakes that occurred beneath the Mount Jailolo complex, collected by the GFZ-Potsdam and BMKG collaborative seismic network over a 12-month period, a negative S-wave velocity anomaly was detected beneath Mount Jailolo at depths below 5 km, which is believed to correspond to a magma chamber. The upper crust at depths of less than 5 km is dominated by positive P- and S-wave velocity anomalies, except in the Idamdehe Caldera Complex, west of the Mount Jailolo complex, which is characterized by negative velocity anomalies. The positive velocity anomalies are believed to represent igneous rocks resulting from past volcanic activity at Mount Jailolo.
This development research aimed to design an Artificial Intelligence (AI)-assisted, Computational Thinking (CT)-based digital worksheet on the Two-Variable Linear Equation System (SPLDV) topic within a deforestation context, and to examine its validity, practicality, and effectiveness in supporting students' mathematical problem-solving skills. Although CT-based worksheets, AI-assisted learning, and environmental contexts have been studied separately, few studies have integrated these three components simultaneously in SPLDV learning; this study addresses that gap. Using the Design Research–Development Studies approach (preliminary research, prototyping, and assessment phases), the study involved grade VIII students of SMP IT Indo Global Mandiri Palembang, selected through purposive sampling (3 students in the one-to-one trial, 6 in the small-group trial, and 20 in the field test). Data were collected through observation, interviews, questionnaires, and tests, then analyzed descriptively and using the Normalized Gain (N-Gain) test and a paired-sample t-test. The digital worksheet was categorized as very valid (95.55%) and very practical (89.7%). Students' average problem-solving score increased from 42.44 to 76.06 (N-Gain = 0.60, medium category; t = 11.13, p < 0.001). Within the scope of this single-school trial, the AI-assisted CT-based digital worksheet shows promise as a contextual mathematics teaching material.
This study aims to develop a Science, Technology, Engineering, and Mathematics (STEM)-based teaching module that integrates the Indigenous Knowledge of the Sade Traditional House into geometry curriculum and to test its validity, practicality, and effectiveness in improving students’ problem-solving skills. This study employed the Research and Development (R&D) method using the ADDIE model, which includes the stages of analysis, design, development, implementation, and evaluation. The research subjects consisted of 69 students: 34 in the experimental class and 35 in the control class. The research instruments included an expert validation sheet, a student response questionnaire, and problem-solving ability tests in the form of pretests and posttests. The expert validation results showed a percentage of 88%, categorized as highly valid, while student responses yielded a percentage of 86.18%, categorized as highly practical. An analysis of learning outcomes showed that the average pretest score for the experimental class increased from 33.76 to 74.85 on the posttest, while the control class’s score increased from 36.89 to 41.63. The results of the independent samples t-test showed a significant difference between the two classes on the posttest (p < 0.001), proving that the developed teaching module was effective in improving students’ problem-solving skills. The integration of Indigenous Knowledge of the Sade Traditional House into geometry instruction created a contextual and meaningful learning experience and strengthened the connection between mathematical concepts and local culture.
Developing students' critical thinking skills has become an increasingly important educational priority in the era of artificial intelligence. Despite the growing use of Augmented Reality (AR) in education, empirical evidence regarding its effectiveness in fostering elementary school students' critical thinking in science remains limited, particularly when integrated with Problem-Based Learning (PBL). This study investigated the effect of AR-assisted PBL on elementary students' critical thinking skills in science. A quasi-experimental design with a non-equivalent pretest–posttest control group was employed involving 62 fifth-grade students (experimental group = 32; control group = 30). Both groups received identical problem-based science instruction on flora and fauna topics, while AR was integrated only into the experimental group. Students' critical thinking skills were assessed using an essay-based instrument developed according to the RED framework (Recognizing Assumptions, Evaluating Arguments, and Drawing Conclusions). Descriptive statistics and inferential analyses were conducted using an independent-samples t-test for the pretest and a one-tailed Mann–Whitney U test for the posttest. The findings revealed that students receiving AR-assisted PBL achieved significantly higher critical thinking scores than those receiving problem-based learning without AR (posttest mean = 81.72 vs. 75.83; p = 0.005), with a moderate educational effect (r = 0.329). These findings suggest that integrating interactive three-dimensional visualization within a problem-based learning environment facilitates scientific reasoning and supports the development of critical thinking beyond conceptual understanding alone. This study contributes to the growing literature on technology-enhanced science education by providing empirical evidence that AR functions most effectively as a pedagogical tool when embedded within inquiry-oriented learning environments. The findings also offer practical implications for designing more interactive and student-centered science instruction in elementary schools.
