Abstract:Intercepting a highly maneuvering moving target remains a difficult planning problem because the target may change heading, accelerate, halt, or reverse without warning, while the pursuer only receives noisy position observations.…
ervations. This study proposes the Adaptive Pursuit Route Algorithm (APRA), an interception path-planning method that combines short-horizon target-state estimation, time-to-go aim-point projection, dynamically weighted cost terms, and a bounded residual that is learned online from past prediction errors. APRA is evaluated against three classical pursuit laws-Pure Pursuit, Proportional Navigation (PN), and Augmented PN (APN)-on a physics-based synthetic dataset of 3,200 trajectories spanning eight motion regimes, yielding 12,800 engagements. APRA attains the best result on every metric: an interception rate of 90.91% (95% CI 0.899-0.919), the shortest mean interception time (9.65 s), the lowest mean prediction error (8.73 units), the highest path efficiency (0.798), and the lowest control energy (48,022). One-way ANOVA confirms that the differences in time, energy, and prediction error are statistically significant (p < 0.001), and a Welch t-test shows APRA is significantly faster than APN (t = -14.48, p < 0.001). The results indicate that disciplined filtering combined with bounded online adaptation is more robust against deceptive and abrupt maneuvers than raw lead-based guidance.
Abstract:This study was designed to improve student learning engagement using the Make a Match cooperative learning model for students at Tanjungbalai Polytechnic. The learning engagement in this study focused on physical and mental…
tal engagement. This study employed Classroom Action Research (CAR), where the lecturer acted as the learning implementer while the researcher acted as the observer. The design of the study employed the Kemmis and Mc. Taggart model. This study was conducted in the even semester. The subjects were students at Tanjungbalai Polytechnic. The object of the study was the participants' learning engagement, and data collection techniques used observation and interviews. The data were analyzed descriptively and presented in tables and graphs. The results showed an increase in student learning engagement in siklus I, reaching 80.10% (good category), and then in siklus II, increasing to 90.10% (very good category). This represents a 9.54% increase. Therefore, the use of the Make a Match cooperative learning model in courses at Tanjungbalai Polytechnic is
Abstract:The mental health of final year students is an important aspect in the world of higher education, especially in facing the demands of completing a thesis at the Faculty of Engineering, Asahan University. However, until now…
ow there is no system that can help assess students' mental health levels in a structured and automatic manner. Therefore, this research aims to design and build an expert system application using the Sugeno Fuzzy Inference System (FIS) method based on PHP and MySQL to assess the mental health level of final year students. The data used in this research was obtained through distributing questionnaires to final year students at the Faculty of Engineering, Asahan University. The variables used include stress intensity, sleep quality, academic load, and social interaction. The data obtained was 99 final year student respondents. The data processing was carried out using the FIS Sugeno method by forming fuzzy sets, membership functions, and 81 fuzzy rules to produce students' mental health levels. Based on the results of system testing, the FIS Sugeno method was successfully applied to automatically assess students' mental health levels. The system is capable of carrying out data input processes, fuzzification, fuzzy inference, and producing assessment output quickly and in a structured manner. The benefit of this research is that it helps provide an initial picture of the mental health conditions of final year students so that it can be taken into consideration in efforts to treat and assist students.
Abstract:The study aims to analyze the effect of the Discovery Learning model assisted by the interactive media Quizizz on students' critical thinking skills in mathematics at SMK Swasta Al-Ma'shum Sidodadi. The main background of…
f this study is the low level of students' critical thinking skills in solving complex problems. The research method used was a quasi-experimental design with a nonequivalent control group design. The research sample consisted of the experimental class (Xth-2) implementing the Discovery Learning model assisted by Quizizz and the control class (Xth-1) using direct learning. Data were collected through a critical thinking skills test in the form of essay questions measuring indicators of interpretation, analysis, evaluation, and inference. The results of the data analysis showed a significant increase in the average critical thinking skills in the experimental class (80.65) compared to the control class (66.41). Hypothesis testing using an Independent Samples T-Test in SPSS 20 yielded a significance value of 0.000 < 0.05. These findings confirm that the integration of the discovery learning model with the Quizizz gamification media has a significant positive impact on improving students' critical thinking skills.
Abstract:The rapid development of information technology has encouraged the healthcare sector to utilize data as a basis for faster, more precise, and effective decision-making. One of the largest data sources in the healthcare sector…
ector is BPJS (Social Security Administration for Health) patient data, which includes medical history, examination results, previous medical procedures, and medication use. This data is a critical asset that, when properly managed and analyzed, can assist hospitals and healthcare facilities in determining appropriate medical interventions for patients. The purpose of this study was to design and develop an application for prioritizing medical procedures for BPJS patients in, using the KNN method, the PHP programming language, and a MySQL database. The data used in this study were BPJS patient visit data. Based on test results at various levels of K=3, K=5, and K=7, the data demonstrated very high consistency. Even though the K value (number of nearest neighbors) was increased from 3 to 7, the final classification results still showed a predominance of the Medium Priority category. With a KNN-based classification system, medical personnel no longer need to manually assess each patient.
Abstract:Gender change is a legal phenomenon that has generated debate in the Indonesian legal system, particularly regarding the recognition of legal identity for applicants after gender transition. The main problem in this study…
y lies in the absence of legal regulations that specifically and comprehensively regulate the procedures, requirements, and legal consequences of gender change, resulting in disparities in court decisions. This study aims to analyze the legal vacuum related to gender change in Indonesia, the legal consequences of determining gender change on population administration, and to comparatively analyze the judges' considerations in Decision Number: 195/Pdt.P/2021/PN.Jkt.Utr and Decision Number 30/Pdt.P/2022/PN.Pwt. The research method used is normative legal research with a statutory approach, a conceptual approach, and a case approach. The research results show that the regulation of gender reassignment in Indonesia is still limited to aspects of population administration, as stipulated in Article 56 paragraph (1) of Law Number 23 of 2006 concerning Population Administration in conjunction with Law Number 24 of 2013. The absence of substantive regulations causes judges to rely on legal findings in deciding gender reassignment requests. The legal consequences of gender reassignment include changes in population identity, civil legal status, and implications for marriage and inheritance. In Decision Number 195/Pdt.P/2021/PN.Jkt.Utr, the judge used a progressive, human rights-based approach, resulting in the granting of the request. Whereas in Decision Number 30/Pdt.P/2022/PN.Pwt, the judge used a normative, moral, and religious approach, resulting in the rejection of the request. This disparity demonstrates the lack of legal certainty regarding gender reassignment in Indonesia.
Abstract:Abstract: This study aims to determine the effect of customer experience on customer loyalty at PT. KAI Divre I North Sumatra. This study uses a quantitative approach with a simple linear regression method. The research…
sample consisted of 209 customers who had used the services of PT. KAI Divre I North Sumatra at least twice, with the sampling technique using the accidental sampling method. The results of the analysis indicate that there is a significant influence between customer experience and customer loyalty. Based on the hypothesis test using simple linear regression, a significance value of p<0.001 (p<0.05) wasa obtained, so the hypothesis in this study was accepted. The regression equation is known as Y=12.051+0.627X, which means that every 1 point increase in the customer experience variable will increase customer loyalty by 0.627. the coefficient of determination (R2) value of 0.753 indicates that customer experience contributes 75.3% to customer loyalty, while 24.7% is influenced by other factors outside the study. The results of the descriptive analysis show that the empirical average of customer loyalty (65.21) is higher than the hypothetical average (47.5), while the empirical average of customer experience (84.72) is also higher than the hypothetical average (62.5). this indicates that customer loyalty is in the medium category, while customer experience is in the high category. Based on these results, it can be concluded that customer experience is a crucial factor in increasing customer loyalty at PT. KAI Divre I North Sumatra.
Keywords: Customer Experience, Customer Loyalty, PT. KAI.
Abstrak: Penelitian ini bertujuan untuk mengetahui pengaruh customer experience terhadap loyalitas pelanggan pada PT. KAI Divre I Sumatera Utara. Penelitian ini menggunakan pendekatan kuantitatif dengan metode regresi linear sederhana. Sampel penelitian berjumlah 209 pelanggan yang telah menggunakan layanan PT. KAI Divre I Sumatera Utara minimal dua kali, dengan teknik pengambilan sampel menggunakan metode accidental sampling. Hasil analisis menunjukkan bahwa terdapat pengaruh signifikan antara customer experience terhadap loyalitas pelanggan. Berdasarkan uji hipotesis menggunakan regresi linear sederhana, diperoleh nilai signifikansi p < 0,001 (p < 0,05), sehingga hipotesis dalam penelitian ini diterima. Diketahui persamaan regresi Y = 12,051+0,627X, yang berarti setiap kenaikan 1 poin pada variabel customer experience akan meningkatkan loyalitas pelanggan sebesar 0,627. Nilai koefisien determinasi (R²) sebesar 0,753 menunjukkan bahwa customer experience memberikan kontribusi sebesar 75,3% terhadap loyalitas pelanggan, sedangkan 24,7% dipengaruhi oleh faktor lain di luar penelitian. Hasil analisis deskriptif menunjukkan bahwa rata-rata empiris loyalitas pelanggan (65,21) lebih tinggi dibandingkan rata-rata hipotetik (47,5), sedangkan rata-rata empiris customer experience (84,72) juga lebih tinggi dibandingkan rata rata hipotetik (62,5). Hal ini menunjukkan bahwa loyalitas pelanggan berada pada kategori sedang, sementara customer experience berada pada kategori tinggi. Berdasarkan hasil tersebut, dapat disimpulkan bahwa customer experience merupakan faktor penting dalam meningkatkan loyalitas pelanggan pada PT. KAI Divre I Sumatera Utara.
Kata Kunci: Customer Experience, Loyalitas Pelanggan, PT. KAI
Abstract: Higher education institutions are required to produce graduates who are competitive in the job market, yet tracer study data is often analyzed only descriptively, leaving deeper patterns unexplored. This study proposes…
ses an integrated approach combining Random Forest, SHAP (SHapley Additive exPlanations), and fairness evaluation to analyze alumni career outcomes. Data were sourced from the 2024 tracer study of Universitas Royal, comprising 466 alumni records with a binary target variable indicating employment status. Preprocessing included missing value handling, one-hot encoding, and stratified train-test splitting with an 80:20 ratio. Class imbalance was addressed using the class_weight='balanced' parameter. The Random Forest model achieved an accuracy of 95.7%, F1-score of 0.946, and AUC-ROC of 0.938, significantly outperforming the dummy baseline of 58.5%. Cross-validation across five folds yielded a mean accuracy of 96.4%, confirming model stability. SHAP analysis revealed that features related to educational level appropriateness and relevance of study field to current occupation were the most dominant predictors. Fairness evaluation per study program showed minimal performance disparity between Sistem Informasi (94.7%) and Sistem Komputer (100%), indicating no significant predictive bias. This framework demonstrates that explainable and fair machine learning can serve as a reliable foundation for evidence-based academic policy making
Abstract:Abstract: The advancement of generative artificial intelligence (AI) opens new opportunities in precision agriculture, particularly in plant health monitoring and diagnosis. This study aims to systematically review studies…
es discussing the use of Generative AI in plant health monitoring from 2019 to 2024. The method used is a Systematic Literature Review (SLR) following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Searches were conducted on Google Scholar, Scopus, Science Direct, and Portal Garuda databases using defined keywords. Of the 247 identified articles, 38 articles met the inclusion criteria and were analyzed in depth. The results show that Generative AI technologies, especially Generative Adversarial Networks (GAN), Diffusion Models, and vision-based Large Language Models (LLMs), have significantly contributed to plant disease detection, image data augmentation, and agronomic recommendation systems. Disease detection accuracy using GAN-based approaches averaged 94.7%, while visual transformer-based models recorded accuracy up to 96.3%. Key barriers include limited labeled datasets, technology gaps in rural areas, and lack of model adaptation to local Indonesian plant varieties. This study concludes that integrating Generative AI in plant health monitoring systems has great potential but requires multidisciplinary collaboration, local dataset development, and appropriate technology adoption policies.
Keywords: Generative AI, GAN, Plant Health, Monitoring, Systematic Literature Review, Precision Agriculture
Abstrak: Perkembangan kecerdasan buatan (AI) generatif membuka peluang baru dalam bidang pertanian presisi, khususnya dalam monitoring dan diagnosis kesehatan tanaman. Penelitian ini bertujuan untuk mengkaji secara sistematis berbagai studi yang membahas pemanfaatan Generative AI dalam monitoring kesehatan tanaman dari tahun 2019 hingga 2024. Metode yang digunakan adalah Systematic Literature Review (SLR) dengan mengikuti protokol PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Pencarian dilakukan pada basis data Google Scholar, Scopus, Science Direct, dan Portal Garuda menggunakan kata kunci yang telah ditetapkan. Dari 247 artikel yang teridentifikasi, sebanyak 38 artikel memenuhi kriteria inklusi dan dianalisis secara mendalam. Hasil kajian menunjukkan bahwa teknologi Generative AI, terutama Generative Adversarial Networks (GAN), Diffusion Model, dan Large Language Model (LLM) berbasis visi, telah memberikan kontribusi signifikan dalam deteksi penyakit tanaman, augmentasi data citra, dan sistem rekomendasi agronomis. Tingkat akurasi deteksi penyakit menggunakan pendekatan berbasis GAN mencapai rata-rata 94,7%, sedangkan model berbasis transformer visual mencatat akurasi hingga 96,3%. Hambatan utama yang ditemukan meliputi keterbatasan dataset berlabel, kesenjangan teknologi di wilayah pedesaan, serta kurangnya adaptasi model terhadap varietas tanaman lokal Indonesia. Penelitian ini menyimpulkan bahwa integrasi Generative AI dalam sistem monitoring kesehatan tanaman memiliki potensi besar namun memerlukan kolaborasi multidisiplin, pengembangan dataset lokal, dan kebijakan adopsi teknologi yang tepat.
Kata Kunci: Generative AI, GAN, Kesehatan Tanaman, Monitoring, Systematic
Abstract:Abstract: This study aims to determine the effect of the Game Based Learning model on students' learning outcomes in Economics subjects for Grade X students at SMA Negeri 1 Percut Sei Tuan in the 2025/2026 academic year.…
This research employed a quasi-experimental method using a pretest-posttest control group design. The population consisted of 356 Grade X students from 10 classes, while the sample included class X-1 as the experimental class and class X-2 as the control class, each consisting of 36 students. Data were collected through observation, interviews, documentation, and tests. Data analysis was conducted using normality tests, homogeneity tests, and hypothesis testing through the Independent Sample T-Test. The results showed that the average posttest score of the experimental class was 86.11, which was higher than that of the control class at 72.56. The hypothesis test yielded a significance value of 0.000 < 0.05, indicating that Ha was accepted and H0 was rejected. These findings demonstrate that the Game Based Learning model has a significant effect on students' learning outcomes. Therefore, the implementation of the Game Based Learning model can be considered an effective alternative for improving students' learning outcomes in Economics subjects.
Keywords: Game Based Learning; Learning Outcomes; Economics Education; Quasi Experiment; Innovative Learning.
Abstrak: Penelitian ini bertujuan untuk mengetahui pengaruh model pembelajaran Game Based Learning terhadap hasil belajar siswa pada mata pelajaran Ekonomi kelas X di SMA Negeri 1 Percut Sei Tuan Tahun Ajaran 2025/2026. Penelitian ini menggunakan metode quasi experiment dengan desain pretest-posttest control group design. Populasi penelitian berjumlah 356 siswa kelas X yang terdiri dari 10 kelas, sedangkan sampel penelitian adalah kelas X-1 sebagai kelas eksperimen dan kelas X-2 sebagai kelas kontrol yang masing-masing berjumlah 36 siswa. Teknik pengumpulan data dilakukan melalui observasi, wawancara, dokumentasi, dan tes. Analisis data menggunakan uji normalitas, uji homogenitas, dan uji hipotesis (Independent Sample T-Test). Hasil penelitian menunjukkan bahwa rata-rata nilai posttest kelas eksperimen sebesar 86,11 lebih tinggi dibandingkan kelas kontrol sebesar 72,56. Hasil uji hipotesis memperoleh nilai signifikansi sebesar 0,000 < 0,05, sehingga Ha diterima dan H0 ditolak. Temuan ini menunjukkan bahwa model pembelajaran Game Based Learning berpengaruh signifikan terhadap hasil belajar siswa. Dengan demikian, penerapan model pembelajaran Game Based Learning dapat menjadi alternatif yang efektif dalam meningkatkan hasil belajar siswa pada mata pelajaran Ekonomi.
Kata Kunci: Game Based Learning; Hasil Belajar; Ekonomi; Quasi Experiment; Pembelajaran Inovatif.