Publication Search

Epilepsy is one of the most common chronic neurological disorders in children. Long-term use of antiepileptic drugs carries the risk of Drug Related Problems (DRPs) such as drug interactions, inappropriate dosing, and untreated indications. This study aimed to identify the types and incidence of DRPs in pediatric epilepsy outpatients at Embung Fatimah General Hospital, Batam. This was a descriptive, non-experimental study with a retrospective design. Data were collected from pediatric medical records (<18 years) between January–December 2024, with a total of 45 patients. DRPs were identified using the American Society of Hospital Pharmacist (ASHP) classification. Of 45 patients, the majority were aged 1–5 years (38%) and female (53%). The most frequently used antiepileptic drug was sodium valproate (56.36%). Identification DRPs included drug interactions (63.16%), untreated indications (5.26%), and inappropriate drug selection (5.26%). No cases of overdose or failure to receive medication were found. The most dominant DRP in pediatric epilepsy patients was drug interactions, particularly between valproic acid and folic acid.

Globalization is a major phenomenon that brings rapid changes in the mindset, behavior, and culture of society, including students in formal educational settings. This condition presents significant challenges for Islamic Religious Education, which plays a crucial role in shaping character and internalizing Islamic values. This study aims to analyze how globalization influences students’ understanding, attitudes, and practices of Islamic values, as well as how Islamic Religious Education can respond adaptively to these changes. This research employs a qualitative approach using a literature study method that reviews books, scholarly articles, and relevant documents related to globalization, Islamic education, and character formation. Data were analyzed through processes of collection, classification, and interpretation to identify patterns of global influence on Islamic values. The findings reveal that globalization offers two major impacts: opportunities for the development of religious literacy through technological and informational access, and threats in the form of external values such as hedonism, individualism, and decreasing religious sensitivity. These findings highlight the need for educational strategies that balance the use of technology with the reinforcement of Islamic character, including the integration of Islamic values into digital-based learning, strengthening teacher role modeling, and habituating moral behavior within school activities. The implications of this study emphasize the importance of innovation in Islamic Religious Education to maintain the relevance of Islamic values amid the ongoing developments of globalization.

Swimming performance is strongly influenced by aerobic endurance, which enables athletes to maintain speed, technique efficiency, and physiological stability during prolonged activity. However, quantitative data regarding aerobic endurance levels among club-level swimmers in Indonesia remain limited. This study aimed to describe the aerobic endurance level of athletes from the Science Swimming Team. A descriptive research design was employed involving 11 swimmers selected through purposive sampling. Data were collected using the Cooper Swimming Test conducted over a 15-minute freestyle swimming session, and aerobic capacity was estimated through VO₂max values. The collected data were analyzed descriptively to classify aerobic endurance levels based on established normative categories by sex and age. The findings indicated that most athletes achieved good to very good performance in swimming distance; however, VO₂max classifications showed that aerobic capacity was predominantly in the moderate category, with only one female athlete reaching an excellent level. This disparity suggests that favorable distance performance does not necessarily reflect optimal aerobic capacity. The results imply the need for more targeted training programs focusing on improving VO₂max through structured aerobic and interval-based training. These findings provide practical input for coaches in designing data-driven and individualized training strategies to enhance aerobic endurance and competitive performance in swimming athletes.

This study aims to determine the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, and to determine whether the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, complies with PSAP No. 07 concerning Fixed Asset Accounting. This study used a qualitative descriptive research method, using triangulation (a combination of observation, interviews, and documentation) as data collection techniques at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province. The results of this study indicate that the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, in terms of classification, recognition, measurement, cost components, post-acquisition expenditures, depreciation, retirement, and disposal, complies with PSAP No. 07 concerning Fixed Asset Accounting. Disclosure of fixed assets regarding the reconciliation of the recorded amount at the beginning and end of the period and depreciation information including the depreciation value, gross recorded value and accumulated depreciation at the beginning and end of the period is in accordance with PSAP Number 07 of 2010 concerning Fixed Asset Accounting. However, for the basic information on the valuation used to determine the recorded value, depreciation information in the form of the depreciation method used and the useful life or depreciation rate used is not in accordance with PSAP Number 07 of 2010 concerning Fixed Asset Accounting.

This literature study evaluates the accuracy of the Slope Mass Rating (SMR) method for coal mine slope stability in Indonesia through a systematic descriptive synthesis of 25 empirical studies from 2020 to 2025. The objectives of the study were to identify the level of SMR prediction accuracy, factors affecting the method's performance, and modifications required for local Indonesian conditions. The research method involved a systematic search with inclusion criteria for empirical studies reporting SMR and/or Safety Factor (SF) values ​​for coal mines and associated slopes in Indonesia. Quantitative analysis showed a range of reported SMR values ​​between 41 and 96 with a median of 72, while SF values ​​ranged from 1.137 to 4.09 for normal operational conditions. The synthesis results indicated that SMR provides a consistent stability classification for initial slope design and failure mode identification (planar, wedge, toppling), with historical validation showing a correlation of up to 91.23% between SMR-based hazard zoning and actual field events in some cases. Key limitations include dependence on discontinuity data quality, sensitivity to groundwater conditions and tropical weathering, and variation in the interpretation of adjustment factors F1-F4. Modifications such as NAAF23 and integration with numerical modeling have been shown to improve prediction reliability. It is recommended that coal mining practitioners combine SMR with kinematic analysis and limit equilibrium modeling as standard operating procedures, and develop adjustment factors specific to Indonesian geological conditions. Further research should focus on standardizing parameter reporting and cross-site quantitative validation to enable more robust statistical meta-analyses.  

Electronic Medical Record (EMR) is an essential component of hospital digital transformation aimed at improving administrative efficiency and service quality. This study aims to analyze the factors influencing the implementation of EMR in outpatient registration at a private hospital in North Jakarta. A mixed-methods design was employed, combining quantitative data collected from questionnaires completed by 30 registration staff with qualitative data obtained through structured interviews and direct observation. The logistic regression analysis revealed that Training and Staff Competence (X2) had a significant positive effect on outpatient registration (OR 30.663; p=0.040), while System Integration and Data Security (X4) also showed a significant effect (OR 15.121; p=0.047). In contrast, Technological Infrastructure Readiness (X1) was positive but not significant (p=0.112), and Organizational Culture and Managerial Support (X3) was negative and not significant (p=0.954). Simultaneously, the model explained 72.1% of the variation in registration effectiveness (Nagelkerke R²=0.721) with a classification accuracy of 93.3%. Qualitative findings supported the quantitative results, highlighting insufficient staff training, persistent technical issues in BPJS system bridging, and difficulties faced by elderly patients in adapting to digital registration. Elderly patients still required staff assistance and simple educational media such as tutorial videos displayed in hospital waiting areas. This study concludes that staff competence and system integration are the key determinants of successful EMR implementation in outpatient registration. It is recommended that hospitals strengthen continuous training programs, improve network and server stability, and expand patient education initiatives to ensure effective, efficient, and patient-friendly digital services.

Information system security faces serious challenges due to increasingly complex cyber attacks. Intrusion Detection Systems (IDS) require efficient approaches to handle high-dimensional data such as the NSL-KDD dataset with 41 features. This study aims to implement the Genetic Algorithm (GA) for feature selection on the NSL-KDD dataset to improve the efficiency and accuracy of network attack detection. The method used is computational experimental research, involving data preprocessing, GA implementation for feature selection, building a classification model using Random Forest, and performance evaluation based on accuracy, precision, recall, F1-score, and computation time. The results show that GA successfully reduced features from 41 to 12 features (70.7% reduction), significantly improving computational efficiency. However, model accuracy slightly decreased from 0.4973 to 0.4951, indicating that while GA is effective for feature selection, the elimination of certain features may reduce classification capability. The implication of this study is that GA can be used as a tool to simplify intrusion detection models, but it should be combined with parameter optimization and data imbalance handling to achieve more optimal performance.  

Coffe is one of Indonesia’s leading commodities, known for its diverse flavors and aromas. Traditionally, coffee quality assessment is conducted manually through cupping tests performed by expert panelists. However, this method is subjective and requires considerable time and cost. This study aims to implement an Artificial Neural Network (ANN) using the backpropagation algorithm to classify coffee types based on sensory parameters such as flavor, aroma, acidity level, and body. Simulated data were generated from five common Indonesian coffee varieties: Arabica Gayo, Robusta Lampung, Arabica Toraja, Liberica Jambi, and Excelsa. The results show that the ANN-based classification system with a 4-8-1 architecture achieved an accuracy rate of 93% after 500 training epochs, with a final error value of 0.07. The implementation of this method provides an efficient and objective technological alternative to assist the coffee industry in maintaining product quality and automatically identifying coffee types.    

The world of work is an environment related to the work we are currently in. In other words, it is a place where various individuals perform an activity. The quality of college graduates is not only seen in terms of high or good grades / GPA. There are many other considerations, where large companies see a potential possessed by the person concerned. The dataset in this study was taken from student respondents about the world of work. One way to classify the influence of competence on the world of work in machine learning is to use datasets as training data so that performance testing can be carried out with the right classification method. From the results of the tests carried out, it is concluded that the results of the comparison are different, which shows the accuracy value of KNN which is around 96%, while the results of the SVM accuracy tested are 98%, so that the accuracy of SVM is better than KNN.

This study aims to analyze the forms of assertive persuasion found in a collection of song lyrics by The Peal by employing a pragmatic approach, specifically Searle’s classification of speech acts. The focus of the research is to examine how the lyrics represent assertive functions as a means of conveying messages, attitudes, and perspectives intended by the songwriter. This study uses a descriptive qualitative method involving several stages: listening closely to the lyrics, identifying linguistic indicators of assertive persuasion, and explaining the meanings and communicative functions embedded in the utterances.The findings reveal that six selected songs by The Peal contain various forms of assertive persuasion. The song Isak Tangis demonstrates an assertive act of warning, while Berbahagialah reflects an act of suggesting. The song Porak Poranda represents the act of complaining, whereas Kehancuran shows elements of asserting or criticizing. The song Cinta Mana yang Kau Bela? contains elements of boasting, and Belum Waktunya reflects the act of reporting or presenting information. These results indicate that The Peal’s song lyrics function not only as artistic expressions but also as persuasive communicative media that convey social and emotional messages through diverse assertive speech acts.

Open fractures are serious orthopedic injuries with a high risk of infection and soft tissue complications. A 20-year-old male patient presented to the Emergency Department with severe pain in his left leg and wrist, accompanied by a laceration on his face, following a traffic accident. Physical examination revealed deformity and an open wound on the left leg, along with severe swelling and tenderness. Radiographic results showed an open fracture of the proximal third of the left tibia and fibula, an open fracture of the left pedal metatarsal, a closed fracture of the distal phalanx of the third digit of the left foot, and a closed fracture of the distal third of the left radius with distal radioulnar joint dislocation. Based on the Gustilo–Anderson classification, the case was categorized as type IIIB. The patient received initial management including debridement, broad-spectrum antibiotics, analgesics, and splinting. Surgical intervention was performed in stages, comprising Open Reduction External Fixation (OREF) for the tibia–fibula and left foot, followed by Open Reduction Internal Fixation (ORIF) for the distal left radius. Postoperative evaluation showed clinical improvement with reduced pain, decreased edema, and improved extremity function. This case emphasizes the importance of rapid and appropriate management of multiple open fractures to prevent infection, maintain bone stability, and accelerate the healing process.

This study aims to determine (1) the forms of legal protection that exist in Indonesia in protecting children from negative visual and verbal content in online games, and (2) the legal responsibility of online game electronic system organizers for exposure to negative visual and verbal content in children. The type of research used is normative juridical with a statutory and conceptual approach. The data used are secondary data obtained through document studies, with qualitative descriptive analysis techniques. The results of the study show that legal protection for children from negative visual and verbal impacts in online games is regulated through various regulations, including Law Number 35 of 2014 concerning Child Protection, Law Number 11 of 2008 concerning Electronic Information and Transactions, Government Regulation Number 71 of 2019 concerning the Implementation of Electronic Systems and Transactions, and Regulation of the Minister of Communication and Information Technology Number 5 of 2021 and Number 2 of 2024. However, its implementation still faces obstacles such as weak age verification, non-objective independent classification, and easily circumvented language filtering. The legal responsibility of online game electronic system organizers for negative visual and verbal content on children can result in administrative or criminal sanctions, according to the Child Protection Law and iRegulation of ithe Minister iof Communication and Information Technology Number 5 of 2021.

This study aims to develop and evaluate an adaptive hybrid weather prediction model that combines pattern classification techniques with a deep learning approach to improve forecasting accuracy, especially for extreme weather events. Using a quantitative-based Research and Development (R&D) approach, this study utilizes ten years of daily rainfall time series data from the Juanda Meteorological Station. The method developed comprises three main phases: weather pattern classification using K-Means clustering to separate normal and extreme patterns; development of a specialist prediction model using SARIMA for seasonal patterns and LSTM for non-linear patterns; and integration of both models into a single adaptive framework. The results show that the adaptive hybrid model performs significantly better than the single model, with a Mean Absolute Percentage Error (MAPE) of 8.76% and a Root Mean Square Error (RMSE) of 9.13%. The main contribution of this study is the development of an intelligent, accurate prediction framework with strong potential for integration into the national early warning system, thereby supporting more effective disaster mitigation efforts in Indonesia. Further research is recommended to validate the model in various regions and add additional climate variables to improve prediction accuracy.

Kerusakan jalan merupakan permasalahan umum yang berdampak langsung terhadap keselamatan dan kenyamanan pengguna jalan, serta terhadap efisiensi transportasi. Selama ini, proses inspeksi jalan masih dilakukan secara manual, yang memerlukan waktu, biaya, dan sumber daya yang tidak sedikit. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi otomatis guna mendeteksi kerusakan jalan berdasarkan citra permukaan, dengan memanfaatkan metode Convolutional Neural Network (CNN). Dataset yang digunakan dalam penelitian ini terdiri dari 400 gambar dengan distribusi seimbang, yaitu 200 gambar kategori Cracks (jalan retak) dan 200 gambar kategori non-Cracks (jalan tidak retak), yang diambil dari sumber dataset terbuka di platform Mendeley Data. Arsitektur CNN dirancang secara khusus dengan empat lapisan konvolusi yang dilengkapi fungsi aktivasi ReLU, pooling layer, dropout layer untuk mengurangi overfitting, serta fully connected layer pada tahap akhir klasifikasi. Proses pelatihan dilakukan menggunakan TensorFlow dan Keras di platform Google Colab, dengan pembagian data sebesar 80% untuk data pelatihan dan 20% untuk data validasi. Hasil evaluasi menunjukkan bahwa model memiliki performa klasifikasi yang sangat baik. Berdasarkan rata-rata dari seluruh skenario pelatihan (epoch 30, 40, dan 50), model CNN yang dikembangkan mampu mencapai akurasi keseluruhan sebesar 97,50%, presisi rata-rata 96,77%, recall rata-rata 99,37%, dan F1-score rata-rata 97,72%. Dengan kinerja yang konsisten dan tingkat kesalahan yang rendah, model CNN ini memiliki potensi besar untuk diterapkan sebagai alat bantu dalam proses identifikasi kerusakan jalan berbasis citra secara otomatis dan efisien, sehingga dapat mempercepat inspeksi, mengurangi beban kerja manual, dan membantu instansi terkait dalam pengambilan keputusan pemeliharaan infrastruktur jalan secara tepat waktu.

Deteksi awal gagal jantung sangat krusial untuk mengurangi angka sakit dan kematian. Metode machine learning, khususnya klasifikasi yang berbasis decision tree, menunjukkan potensi untuk mendukung keputusan medis dengan memisahkan pasien berisiko menggunakan variabel klinis yang biasa. Tujuan penelitian ini adalah untuk merancang dan menilai model Decision Tree dalam mengklasifikasikan pasien dengan gagal jantung menggunakan data klinis yang bersifat publik. Langkah-langkah dalam penelitian mencakup preprocessing (mengatasi nilai yang hilang, normalisasi, dan pemilihan fitur), pelatihan dengan stratified k-fold cross-validation, serta penilaian menggunakan metrik accuracy, precision, recall, F1-score, dan AUC. Hasil dari eksperimen menunjukkan bahwa Decision Tree yang dioptimalkan memberikan performa yang kompetitif serta keunggulan dalam interpretabilitas melalui aturan keputusan yang jelas. Sumbangan penelitian ini meliputi (1) pipeline yang dapat direproduksi untuk klasifikasi gagal jantung (heart failure), (2) kumpulan aturan yang mendukung skrining klinis heuristik, dan (3) perbandingan empiris terhadap metode machine learning lainnya. Temuan ini menunjukkan bahwa Decision Tree dapat menjadi alat skrining awal yang efektif, terutama di tempat dengan keterbatasan sumber daya.

Klasifikasi kualitas biji kopi merupakan langkah penting dalam menjaga mutu dan konsistensi produk kopi, terutama di sektor industri dan agribisnis. Penilaian kualitas secara manual seringkali bersifat subjektif, sehingga dibutuhkan pendekatan berbasis teknologi untuk memberikan hasil yang lebih objektif. Penelitian ini mengusulkan penggunaan arsitektur Convolutional Neural Network (CNN) ResNet50 untuk mengklasifikasikan citra biji kopi berdasarkan tingkat sangraian, yaitu Dark, Medium, Light, dan Green. Dataset yang digunakan terdiri dari 1.600 citra biji kopi, dibagi menjadi data pelatihan (1.200 gambar) dan validasi (400 gambar). Model dikembangkan dengan memanfaatkan bobot pralatih ResNet50 dari ImageNet dengan seluruh layer dasar dibekukan, dan ditambahkan lapisan GlobalAveragePooling2D, Dense, BatchNormalization, Dropout, serta output layer softmax. Pelatihan dilakukan tanpa preprocessing atau augmentasi data. Hasil penelitian menunjukkan bahwa model mampu mencapai akurasi sebesar 99%, dengan precision, recall, dan f1-score yang tinggi dan seimbang pada seluruh kelas. Model kemudian diimplementasikan dalam aplikasi berbasis web menggunakan Streamlit yang memungkinkan pengguna mengunggah citra biji kopi dan memperoleh hasil klasifikasi secara otomatis. Temuan ini menunjukkan bahwa pendekatan ResNet50 efektif untuk mendukung proses penilaian kualitas biji kopi secara cerdas, serta dapat dikembangkan lebih lanjut untuk penerapan di industri.  

Fraud detection on payment transactions is an extremely imbalanced, high-stakes classification task in which deployment decisions depend not only on ranking quality but also on reliable probability estimates. We study credit card fraud detection on a standard real-transaction benchmark (284,807 transactions; 492 frauds) and target two deployment requirements: cost-sensitive thresholding under asymmetric error costs and reliability calibration so model outputs can be interpreted as stable risk scores. We benchmark logistic regression and XGBoost and propose a focal-proxy reweighting scheme for boosted trees via iterative weight updates inspired by focal loss. Probabilities are calibrated on validation using Platt scaling, temperature scaling, and isotonic-style monotone calibration; the best calibrator is selected by minimum validation Brier score. For decision-making, we choose the operating threshold that minimizes expected cost, Cost(t) = 10 · FN(t) + 1 · FP(t), on validation, then evaluate on a held-out test set. On the benchmark split (train 199,364; validation 42,721; test 42,722), the calibrated XGBoost baseline achieves AUROC 0.973, AUPRC 0.812, fraud-class F1 0.767, and expected cost 154 with very low calibration error (ECE = 1.1 × 10⁻⁴). Overall, calibration reduces ECE and improves or maintains the Brier score, while cost-aware thresholding makes the FN/FP trade-off explicit via decision curves. 

Selecting a faculty that aligns with students’ interests and talents is a strategic step in determining the success of higher education and future career paths. However, most vocational high school (SMK) students still face difficulties in identifying the most suitable faculty due to the lack of data-driven analysis. This study implements the C4.5 classification algorithm within data mining techniques to build an automatic and measurable faculty recommendation system. The dataset consists of attributes such as SMK major, interest level, aptitude test results, academic grade average, and gender, with the output being the recommended faculty. The C4.5 algorithm was chosen for its ability to generate a transparent and interpretable decision tree, which helps both guidance counselors and students understand the rationale behind the recommendations. The experimental results show that the constructed classification model achieved an accuracy rate of 88%, based on cross-validation testing using data from 12th-grade students. The implementation of this system is expected to serve as an objective tool in the faculty selection process and to promote a data-driven decision-making approach in secondary education environments.

The sport of archery requires an accurate and fair classification system of athletes according to international standards. This community service research aims to introduce and implement the ArchiClass application as a technology-based innovation for athlete classification, as well as improve the understanding of the archery community at Al Ayyubi Archery Club Boyolali regarding sports with disabilities. This activity involved 50 athletes and 6 coaches. The methods used include socialization, application demonstration, simulation, and evaluation of participant responses. The results showed that participants gained a better understanding of the importance of fair and technology-based classification. Participants gain practical experience using ArchiClass, while coaches and parents gain new insights into archery. In addition, the implementation of this application encourages the creation of a more transparent and consistent classification process. The final evaluation showed that the majority of participants felt helped by the existence of the application and expressed readiness to implement it in training activities and competitions. This program successfully introduced ArchiClass as an effective tool and increased community awareness and understanding of disability sports.

Tomat merupakan komoditas hortikultura bernilai ekonomi tinggi dengan permintaan pasar yang luas, baik domestik maupun internasional. Salah satu tantangan utama dalam distribusinya adalah menjaga kualitas produk, khususnya tingkat kematangan buah. Penilaian kematangan yang akurat sangat penting karena berdampak pada masa simpan, cita rasa, dan kelayakan konsumsi. Namun, metode konvensional yang mengandalkan pengamatan visual manusia cenderung subjektif, memerlukan banyak tenaga kerja, dan kurang efisien dalam skala besar. Penelitian ini bertujuan mengembangkan sistem klasifikasi tingkat kematangan tomat menggunakan pendekatan transfer learning dengan arsitektur ResNet50. Dataset terdiri atas 2.400 citra yang terbagi ke dalam tiga kelas matang (ripe), belum matang (unripe), dan tidak layak konsumsi (reject). Model dilatih menggunakan teknik fine-tuning pada sepuluh lapisan terakhir dari ResNet50, dioptimalkan dengan algoritma Adam dan learning rate sebesar 0,00001. Hasil evaluasi menunjukkan akurasi validasi rata-rata sebesar 98,08% dengan nilai precision, recall, dan F1-score yang tinggi di semua kelas. Model yang telah dilatih kemudian diimplementasikan dalam aplikasi berbasis web menggunakan kerangka kerja streamlit, yang memungkinkan pengguna mengunggah citra tomat dan memperoleh hasil klasifikasi secara instan melalui antarmuka yang sederhana dan mudah digunakan. Dengan tingkat akurasi yang tinggi serta kemudahan akses, sistem ini berpotensi menjadi solusi praktis untuk mendukung digitalisasi proses penyortiran tomat serta mendorong pemanfaatan teknologi kecerdasan buatan di sektor pertanian.