Universitas Ahmad Dahlan Journal
Not a member yet
5744 research outputs found
Sort by
SEIAR Epidemic Model on the Spread on the Spread of COVID-19 in the Special Region of Yogyakarta
Full text linkSevere Acute Respiratory Syndrome Coronavirus 2 ( SARS-Cov-2) merupakan virus varian baru yang menyebabkan penyakit menular yang disebut dengan Coronavirus Disease (COVID-19). World Health Organization (WHO) menyatakan COVID-19 sebagai pandemi global pada tanggal 11 Maret 2020. Untuk menggambarkan penyebaran COVID-19, pada artikel ini disusun model epidemik SEIAR yang menunjukkan dinamika populasi dari lima kompartmen, yaitu kelompok rentan, kelompok terpapar, kelompok terinfeksi bergejala, kelompok terinfeksi tanpa gejala, dan kelompok sembuh. Hasil penelitian ini diperoleh dua titik kesetimbangan, yaitu titik kesetimbangan penyakit dan titik kesetimbangan endemik. Analisis kestabilan titik kesetimbangan dengan menggunakan kriteria Routh-Hurwitz menunjukkan titik kesetimbangan bebas penyakit bersifat stabil asimtotik lokal pada saat R_0<1 dan tidak stabil pada saat R_0>1 . Selanjutnya, pada prediksi kasus COVID-19 di Daerah Istimewa Yogyakarta yang diperkirakan nilai R_0=1,48. Kemudian dilakukan analisis sensitivitas untuk mengetahui parameter yang paling berpengerauh terhadap bilangan reproduksi dasar. Hasil penelitian menunjukkan laju infeksi (β) merupakan parameter yang paling berpengaruh terhadap penyebaran COVID-19 di Daerah Istimewa Yogyakarta. Hasil penelitian ini diharapkan menjadi salah satu referensi kepada pemerintah Daerah Istimewa Yogyakarta untuk menekan laju infeksi pada kasus penyebaran COVID-19
Implementasi Metode SVM-PSO Dengan Fitur Selection Variance Threshold Pada Klasifikasi Penyakit Diabetes Mellitus
Full text linkPada penelitian ini membahas tentang kasus klasifikasi pada data penyakit diabetes. Metode yang digunakan dalam penelitian ini adalah metode Support Vector Machine yang dioptimalkan dengan algoritma Particle Swarm Optimization guna memperoleh parameter terbaik dengan kombinasi seleksi fitur menggunakan Variance Threshold. Penelitian ini bertujuan untuk mengetahui cara kerja dan hasil akurasi dari metode Support Vector Machine dengan optimasi Particle Swarm Optimization menggunakan seleksi fitur Variance Threshold. Hasil penelitian menggunakan kombinasi metode tersebut menunjukkan hasil akurasi sebesar 80%. Hasil akurasi tersebut lebih tinggi jika dibandingkan dengan metode Support Vector Machine tunggal tanpa optimasi dan seleksi fitur dengan akurasi sebesar 76%. Meningkatkan akurasi sebesar 4% dari 76% menjadi 80%.
 
Comparative Analysis of Deep Learning Models for Retrieval-Based Tourism Information Chatbots
Full text linkDespite significant advancements in deep learning models for chatbots, comprehensive analyses tailored to the tourism sector remain limited. This study addresses the gap by comparing the performance of six prominent models—MLP, RNN, GRU, LSTM, BiLSTM, and CNN—in creating chatbots designed to address traveler needs such as information about facilities, ticket prices, activity suggestions, and operational details. The methodology includes key stages such as data collection, preparation, model training, and evaluation using accuracy, precision, recall, F1-score, and qualitative assessments. The dataset, derived from interviews with managers of 11 tourism destinations, captures critical details to replicate real-world user interactions. The results indicate that the CNN model performed the best, achieving the highest accuracy (0.98), precision (0.99), recall (0.98), and F1-score (0.98), showcasing its ability to effectively handle user queries by identifying relevant patterns in data. While MLP achieved strong accuracy (0.94), its simpler design limited its capacity to manage complex questions. The RNN model had the lowest accuracy (0.82), highlighting its challenges in understanding structured information. These findings confirm CNN as the most effective model for retrieval-based chatbots in tourism, balancing accuracy and practicality. This research offers valuable insights for improving AI-driven tourism tools, providing guidelines for selecting optimal models and enhancing chatbot performance to enrich the traveler experience
Improving understanding of wiggins concept through the application of blended discovery learning model in biology learning
Full text linkStudents are required to have the ability to think, one of which is understanding. In the era of the fast development of information technology, understanding in students is not just knowing facts, but knowing the meaning, and emphasizing the involvement of students in dealing with problems. This research aimed to determine the improvement of students' concept understanding based on Wiggins' aspects of understanding, which are explain, interpretation, application, perspective, empathy and self-knowledge in biology learning by applying a blended discovery learning model. This research is a quasi-experimental research with pretest-posttest control group design. The population in this research were all students of class X Mathematics and Natural Sciences SMAN 1 Sumber in the 2022/2023 academic year with samples of class X Mathematics and Natural Sciences 4 as the experimental class and X Mathematics and Natural Sciences 3 as the control class. Data collection techniques used tests, and questionnaires. The results showed that there were differences in the improvement of students' understanding based on significant aspects of Wiggins' understanding in biology learning using models of blended discovery learning on kingdom plantae material
Adaptation and Psychometric Evaluation of the Indonesian Version of the Career Aspirations Scale-Revised (CAS-R) among Adolescents
Full text linkThe dynamic changes within the world of work require individuals to engage in robust career planning. In this context, career aspiration is understood as a psychological construct reflecting an individual’s hopes, motivations, and goals related to their future employment. This study aimed to adapt and evaluate the psychometric properties of the Career Aspirations Scale-Revised (CAS-R) into Indonesian to provide a valid and reliable measurement tool. The respondents comprised 549 Indonesian adolescents. The adaptation process followed the ITC (2018) guidelines, encompassing content validation, construct validation through Confirmatory Factor Analysis (CFA) and Rasch analysis, as well as reliability testing. The CFA results supported a three-factor structure (RMSEA = 0.034; CFI = 0.990; TLI = 0.990), with 18 items meeting the factor loading criteria. Cronbach’s alpha of 0.910 indicated high reliability. Rasch analysis further supported the instrument’s validity and internal consistency, with 19 items deemed to fit the model. These findings confirm that the Indonesian version of CAS-R is a suitable instrument for measuring adolescents’ career aspirations in Indonesia. It can be used by schools, counselors, and psychological institutions to support career assessment and planning
Prediksi Harga Penutupan Saham BMRI Menggunakan Metode Bidirectional Long Short-Term Memory
Full text linkIn recent years, Indonesia's capital market has grown significantly, with the number of investors rising from 3.8 million in 2020 to 12.3 million in January 2024. This study explores the application of the Bi-LSTM model to predict BMRI stock prices by systematically optimizing 75 models to obtain optimal hyperparameters. Unlike prior trial-and-error approaches, this research employs structured hyperparameter exploration using data splits of 70:30, 80:20, and 90:10 to evaluate model accuracy and stability. Results show excellent performance with a MAPE of 2.182% on BMRI’s historical closing prices from January 1, 2021, to July 31, 2024, using a 2-layer Bi-LSTM architecture, batch size 16, and 150 epochs. The findings confirm that an appropriate model can produce highly accurate predictions. This study provides insight into Bi-LSTM modeling in the banking sector, offering valuable references and strategic considerations for investors and stakeholders based on predictive results
In silico and in vitro studies of flavanoid content of Uncaria gambir Roxb stem extract on antidiabetic activity
Full text linkBajakah Kalalawit (Uncaria gambir Roxb.) is a typical plant of the Dayak tribe of Kalimantan, Indonesia. This study aims to evaluate the antidiabetic potential of Bajakah Kalalawit stem extract through in silico and in vitro approaches. In silico analysis was conducted to identify the interaction of bioactive compounds in 96% ethanol extract of Bajakah Kalalawit stems with the alpha-glucosidase enzyme (PDB ID : 5NN8), which is the main target in the treatment of diabetes. The results of molecular simulations showed that 2 bioactive compounds of the flavonoid group, namely Bikisocoumarin (-8.25 kcal/mol) and Pinostrobin (-5.81 kcal/mol) contained in 96% ethanol extract of Bajakah Kalalawit stems have significant inhibitory potential against the enzyme. Furthermore, in vitro tests were conducted to assess the inhibitory activity against the alpha-glucosidase enzyme and its effect on reducing blood glucose levels. The experimental results showed that 96% ethanol extract of Bajakah Kalalawit stems was able to significantly (ρ < 0.05) inhibit alpha-glucosidase activity (IC50 = 0.296 ± 0.004 μg/mL). This finding indicates that Bajakah Kalalawit has the potential as a source of active antidiabetic ingredients that can be further developed as an alternative therapy for diabetes management
Optimization study on palm fat base (HAMIN®) and purified water proportion in diphenhydramine hydrochloride cream formulation
Full text linkHAMIN® is a self-emulsifying base composed of a mixture of hydrogenated palm kernel oil and hydrogenated palm kernel stearin. This formulation not only enhances the aesthetic quality of products but also simplifies the manufacturing process, as it eliminates the need for additional emulsifying agents to form a stable cream. Due to these properties, HAMIN® is considered highly suitable for the development of both pharmaceutical and cosmetic formulations. Despite its potential applications, no prior research has investigated the optimal ratio of HAMIN® palm fat base to distilled water distilled waterrequired to achieve desirable physical characteristics and drug release properties in cream formulations. Therefore, this study aims to determine the optimum composition of HAMIN® palm fat base and distilled water for the formulation of diphenhydramine hydrochloride cream. The optimization process was conducted using the simplex lattice design (SLD) method, a statistical approach commonly employed to evaluate and optimize multicomponent formulations. The experimental results demonstrated that increasing the concentration of HAMIN® palm fat base had a dominant effect on enhancing the pH, viscosity, adhesion, and stability of the cream. Conversely, a higher concentration of distilled water significantly improved spreadability, extrudability, and drug release flux. These findings indicate that the selection of base composition plays a crucial role in determining the overall performance of the cream formulation. The optimal formulation, as determined through SLD analysis, consisted of 41.667% HAMIN® palm fat base and 48.333% distilled water, achieving a desirability index of 0.649. This composition represents the most balanced formulation in terms of physical stability and drug release, making it a promising candidate for further pharmaceutical and cosmetic applications
Systematic Literature Review: Analisis Forensik Digital untuk Investigasi Cyberbullying di Media Sosial
Full text linkSemakin berkembangnya teknologi membawa perubahan terutama pada gaya hidup, tatanan sosial, hingga moral masyarakat Indonesia. Manifestasi utama dari kemajuan ini adalah teknologi internet serta berbagai platform media sosial yang memungkinkan individu untuk terhubung, berinteraksi, dan berbagi informasi secara cepat dan efisien. Namun, penggunaan media sosial menjadi salah satu sumber kejahatan seperti fenomena cyberbullying. Bukti digital melalui investigasi forensik digital dapat menjadi sumber informasi yang berharga, di samping pernyataan saksi serta komentar tersangka dalam mengungkap sifat kejahatan cyberbullying. Tujuan penelitian ini adalah untuk mengkaji metode dan alat bantu forensik digital dalam kasus cyberbullying di media sosial. Metode yang digunakan berupa Systematic Literature Review (SLR). Hasil review terhadap 30 artikel relevan mengidentifikasi data yang diperoleh dari aktivitas forensik digital dapat berupa log komunikasi, riwayat video, deskripsi pesan, dan interaksi dalam media sosial. Metode investigasi yang digunakan adalah DFRWS, ACPO, NIST, Live Forensics, SVM, NIJ, IDFPM, IDFIF, dan Mobile Forensik. Kakas yang digunakan adalah Cosine Similarity Tool, Live Forensics Tools, SVM Classifier, Hunchly, dan Jaccard Similarity Tools. Platform media sosial yang ditemukan kasus cyberbullying adalah Beetalk, Facebook, IMO Messenger, Instagram, Instagram Messenger, Line Messenger, Michat, Skype, Threads, TikTok, Twitter, WhatsApp, serta WeChat
Predicting Early Lease Termination Risk in Jakarta Shopping Malls Using a SMOTE-Enhanced SVM Model for Financial Loss Prevention
Full text linkThe high incidence of early lease termination in shopping malls poses significant challenges to revenue generation, unit utilization, and the operational stability of commercial properties. The limitations of traditional management practices in identifying high-risk tenants early often result in financial losses and suboptimal asset allocation. To address this issue, this study developed a data-driven predictive model designed to identify the likelihood of early lease termination. The approach integrates the Support Vector Machine (SVM) algorithm with the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance within the dataset. The model development followed the CRISP-DM methodology and utilized a historical dataset comprising 795 lease records from a major shopping mall in Jakarta, spanning the years 2015 to 2022. Through systematic data preprocessing, feature selection, and model optimization using grid search and cross-validation, the model achieved excellent classification performance: 93.10% accuracy, 90.50% precision, 96.40% recall, 93.30% F1-score, and 97.30% AUC. The findings demonstrate that the SMOTE–SVM combination consistently outperforms in detecting minority-class cases. A prototype system was also developed, enabling mall managers to predict tenant risk in real-time through an intuitive user interface. The contributions of this research are twofold. First, it presents a novel application of the SMOTE–SVM approach for addressing data imbalance in early lease termination prediction within the Indonesian commercial property sector an area that remains underexplored. Second, the study delivers a practical and deployable prototype system that enables real-time risk assessment for mall management, thereby bridging the gap between predictive modeling and operational decision-making. Overall, the proposed model offers a reliable and scalable predictive solution that can be adapted for risk management in other commercial property contexts, supporting a data-driven and proactive decision-making approach. However, it is important to note that the applicability of the proposed SMOTE–SVM model may face certain challenges when deployed in different commercial property contexts. Variations in tenant characteristics, market dynamics, economic conditions, and data availability across regions could impact model generalizability and performance. Moreover, the reliance on historical lease data assumes consistency in tenant behavior patterns, which may not hold true in rapidly evolving retail environments or for properties with distinct operational models such as coworking spaces or mixed-use developments. These factors should be carefully considered when adapting the model to ensure its validity and effectiveness outside the original study setting