Publication Search

This study aims to develop a predictive model using linear regression to identify potential arrhythmias in the elderly based on electrocardiogram (ECG) data. Data were collected through observations at healthcare facilities from elderly patients with indications of arrhythmia, then preprocessed such as cleaning, normalization, feature selection, and outlier checking were carried out. The features used include PR interval, QRS duration, QT interval, and heart rate. The dataset was divided into training data (80%) and test data (20%) to build and evaluate the model. The training results showed that the model was able to predict the risk of arrhythmia with a Mean Squared Error (MSE) value of 0.15 and a coefficient of determination (R²) close to 1. Evaluation using a confusion matrix showed an accuracy of 76.19%, precision of 82.80%, recall of 76.19%, and F1 score of 72.70%. These results prove that linear regression can be used as an initial approach in the early detection of arrhythmias non-invasively in the elderly. This study provides a foundation for the development of ECG data-based clinical decision support systems and suggests future exploration of more complex models and integration with real-time monitoring technologies.

Since 2022, the application of the Internet of Things (IoT) in the healthcare sector has grown significantly, marked by the increasing adoption of wearable technology, artificial intelligence (AI), machine learning (ML), and blockchain integration. Research highlights India and China as leading contributors in this domain. IoT enables real-time monitoring of chronic diseases, tracking of patient vital signs, and detection of health protocol compliance. Integrated systems such as Monit4Healthy and RADAR-IoT support personalized medical recommendations and cross-platform interoperability. However, key challenges persist, including patient data privacy and security, system interoperability issues, data fragmentation, and barriers to user acceptance due to cost, digital literacy, and device comfort. Proposed solutions include blockchain for secure data sharing, adaptive congestion control for network performance, and user training to improve technology adoption. Therefore, successful IoT deployment in healthcare requires a comprehensive approach that addresses technological, social, ethical, and sustainability aspects to achieve an effective and inclusive transformation of health services.

This study aims to evaluate and compare the performance of two neural network architectures under the Recurrent Neural Network (RNN) category, namely Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), in predicting earthquake magnitude in Indonesia. The dataset used consists of daily earthquake magnitude records from 2008 to 2023, preprocessed into time series format and normalized using the MinMax method. The training process was conducted using various combinations of batch size and epoch, and evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and relative prediction accuracy. The evaluation results show that LSTM with a batch size of 32 and 50 epochs provides the best prediction performance, achieving a MAE of 0.2227 and 93.65% accuracy. Meanwhile, GRU performed optimally at a batch size of 64 and 50 epochs, with a MAE of 0.2229 and 93.66% accuracy. The prediction visualization shows that LSTM offers greater stability and precision in tracking actual data patterns. These findings indicate that LSTM holds stronger potential for supporting earthquake prediction systems based on time series data.

Credit scoring is an important element in decision-making for providing financing, especially for microfinance institutions. Several methods for predicting credit scoring include Decession Tree, Gradient Boosted, Neural Network, K-NN, and Rule Induction. This study aims to improve the accuracy of financing risk prediction by efficiently integrating historical data. The Neural Network (NN) algorithm is a machine learning algorithm consisting of neurons (nodes) connected to each other in several layers (input, hidden, and output). NN is used for pattern recognition, classification, regression, and complex non-linear modeling. The NN algorithm has the advantage of working well on large and diverse data and unstructured data. However, the NN algorithm has weaknesses such as overfitting and data dependence. In this study, the integration of the Sample Bootstrapping and Weighted Principal Component Analysis (PCA) methods is proposed to improve optimal accuracy in the NN algorithm. The Sample Bootstrapping method is used to reduce the amount of training data to be processed. The Weighted PCA method is used to reduce attributes. This study uses a financing customer dataset. The results of the study show that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA resulted in an accuracy increase of 1-3% (97%-99%) compared to other algorithms. Therefore, it can be concluded that the integration of the NN algorithm with Sample Bootstrapping and Weighted PCA produces better accuracy than other algorithms

This study aims to analyze the factors that influence students' interest in continuing their education to college using a machine learning approach. Data was collected through an online questionnaire completed by 727 students between July 27 and August 22, 2025, covering 23 variables consisting of respondent identity (gender, grade level, major) as well as internal and external factors such as parental support, learning motivation, and preferred type of college. The data preparation stage was carried out through column cleaning, deletion of empty data, encoding of categorical variables, and division of the dataset into 80% training data and 20% test data. The Naive Bayes algorithm of the CategoricalNB type was used because it was suitable for the categorical nature of the data. The evaluation results showed that the model was able to predict student interest with 96% accuracy. For the class of students interested in continuing their studies, the precision, recall, and F1-score values were above 0.95, while the performance in the class of students who were not interested was slightly lower due to the smaller amount of data. These findings show that Naive Bayes is proven to be effective and reliable in classifying students' interest in continuing their studies and can be the basis for decision-making in designing more targeted educational strategies.

This study aims to analyze and compare the performance of the Naive Bayes, K-Nearest Neighbors (KNN), and Decision Tree algorithms in predicting the purchase intention of e-commerce visitors using the Online Shoppers Purchasing Intention Dataset, which consists of 12,330 records and 18 variables, with the Revenue variable serving as the classification target. The preprocessing stage involved transforming categorical and boolean variables into numerical form, standardizing features using StandardScaler, and splitting the dataset into 80 percent training data and 20 percent testing data. Model evaluation was conducted using accuracy, precision, recall, F1-score, and ROC-AUC metrics, and was further strengthened by 10-fold cross-validation to obtain more stable results. The findings indicate that KNN achieved the highest accuracy of 0.866180, while Naive Bayes produced the highest recall value of 0.690998 and the highest ROC-AUC value of 0.821696. Meanwhile, Decision Tree demonstrated relatively balanced performance with an accuracy of 0.857259 and an F1-score of 0.571776, whereas the cross-validation results identified KNN as the model with the highest average accuracy of 0.8770. These findings suggest that the selection of a classification model for purchase intention prediction cannot rely solely on a single evaluation metric, as each algorithm possesses different strengths. Therefore, a comparative approach among algorithms can help determine the most suitable model for supporting consumer behavior analysis on e-commerce platforms.

This study analyzes the prediction of poverty levels in North Sumatra Province by applying the Long Short-Term Memory (LSTM) method based on time series integrated with Google Earth Engine (GEE). Historical poverty data of districts/cities were obtained from the Central Statistics Agency (BPS) and processed using Python in Google Colab for LSTM model training. The prediction results are visualized spatially in the form of thematic maps through GEE to identify areas with high poverty rates. The evaluation model was carried out by calculating MAE, RMSE, MAPE, and prediction accuracy, with most areas having an accuracy above 80%. These findings indicate that this approach is effective in mapping poverty trends and supporting data-driven policies. This predictive model can be the basis for more targeted social interventions and strategies for developing inclusive and sustainable regional development.

E-WOM adalah pernyataan positif atau negatif yang dibuat oleh konsumen potensial, konsumen aktual, dan konsumen terdahulu tentang produk atau perusahaan melalui internet. Salah satu media yang dapat digunakan untuk mendapatkan pernyataan tersebut adalah media sosial twitter. Media sosial dapat digunakan untuk mendapatkan respon secara jujur karena biasanya orang tidak akan merasa sungkan untuk mengungkapkan perasaannya secara tidak langsung. Penelitian ini akan menganalisa ada atau tidaknya pernyataan e-WOM terhadap penyedia jasa layanan internet. Metode yang dilakukan terdiri dari tiga kegiatan, yang pertama adalah mengambil cuitan pengguna twitter yang mengandung kata yang berhubungan dengan penyedia jasa layanan internet. Kegiatan kedua adalah persiapan data untuk training. Yang ketiga adalah menganalisa e-wom dengan metode knn dan bahasa pemrograman R. Hasil penelitian ini berupa data motif e-wom Venting Negative Feelings dan Extraversion / Positive Self-Enhancement. Data tersebut dapat digunakan sebagai pendukung keputusan pengguna internet dalam memilih penyedia jasa layanan internet yang baik.

Neuro Associtive Conditioning Kepolisian Republik Indonesia (NAC POLRI) mempunyai tujuan untuk mengembalikan semangat dan teladan yang telah diwariskan oleh para pejuang dan para pahlawan Indonesia melalui training Pendidikan Karakter.  Kemerosotan bangsa Indonesia, khususnya para generasi penerus bangsa menjadikan bangsa Indonesia terpuruk.  Generasi muda menjadi loyo seperti tak bertenaga di alam Indonesia yang subur dan gemah ripah lohjinawi.  Perkembangan Teknologi Informasi menjembatani Rencana dan kiprah NAC POLRI melalui media online berupa website.  Melalui website nacpolri.org diharapkan semua tujuan dan rencana untuk membuat kembali generasi muda memiliki karakter bangsa Indonesia akan tercapai.  Proses pembuatan website yang dibuat melalui rencana yang benar, develop web yang benar, cara mengisi artikel yang benar dan cara memelihara website yang benar menjadi nilai tambah website nacpolri.org.  Website nacpolri.org menjadi besar dan disukai pengunjung karena menggunakan cara Search Engine Optimization (SEO) dan selalu di evaluasi perkembangannya.  Sehingga tujuan menjadikan bangsa ini kembali memiliki Pendidikan Karakter yang kuat akan bisa diwujudkan.

Lama studi dari mahasiswa ini sangatlah penting bagi mahasiswa, program studi serta perguruan tinggi. Permasalahan lama studi setiap mahasiswa bisa disebabkan atau dipengaruhi oleh banyak faktor. Hal tersebut telah dibuktikan dengan beberapa penelitian pada permasalahan tersebut yang mendapati sejumlah faktor yang berpengatuh terhadap lama studi mahasiswa. Dengan menggunakan teknik data mining khususnya klasifikasi untuk prediksi dengan algoritma naive bayes dapat dilakukan prediksi terhadap ketepatan waktu studi dari mahasiswa berdasarkan data training yang ada. Data training dan testing yang digunakan diambil secara random pada tabel data master yang digunakan. Algoritma naive bayes, menghitung perbandingan peluang antara jumlah dari masing-masng kriteria nilai fields terhadap nilai hasil prediksi sesunggunya. Fungsi untuk prediksi dibuat menggunakan Query pada MySql dalam bentuk function(fbayesian). Dari hasil uji coba diperoleh tingkat kesalahan prediksi berkisar 20% sampai dengan 50% dengan data training dan testing yang diambil secara random. Namun rata-rata tingkat kesalahan berkisar 20 % hingga 34%. Tinggi rendahnya tingkat kesalahan dapat disebabkan oleh jumlah record data dan tingkat konsistensi dari data training yang dgunakan. Sedangkan hasil prediksi dari ketepatan lama studi dari mahasiswa angkatan 2008 adalah sebesar 254 mahasiswa diprediksi ”Tepat Waktu” dan sisanya yaitu 4 orang diprediksi ”Tidak Tepat Waktu”.   Kata Kunci : Prediksi, Lama Studi, Data Mining, Naive bayes, MySql

Salah satu cara yang paling berhasil untuk mengorganisasikan informasi dalam jumlah banyak dan dapat dipahami oleh para pencari informasi adalah dengan melakukan klasifikasi dokumen berdasarkan topiknya. Kebutuhan akan dokumen pembelajaran untuk melakukan klasifikasi dokumen merupakan salah satu permasalahan yang sering muncul dalam topik klasifikasi dokumen. Permasalahan yang timbul menjadi semakin rumit dengan adanya fakta bahwa jumlah simpanan data berita menjadi sangat besar dan tidak terorganisir. Oleh karena itu, diperlukan suatu strategi pengelompokan otomatis dokumen-dokumen berita tersebut. Klasifikasi merupakan salah satu metode dalam data mining yang bertujuan untuk mendefinisikan kelas dari sebuah objek yang belum diketahui kelasnya. Pada klasifikasi terlebih dahulu akan dilakukan proses training dan testing. Pada proses tersebut akan digunakan dataset yang telah diketahui kelas objeknya. Pada penelitian ini akan dibangun aplikasi Klasifikasi Berita Menggunakan Ontologi. Obyek penelitian dari penelitian ini adalah artikel berita berbahasa Indonesia dari situs http://www.google.com Dengan adanya klasifikasi dokumen maka hasil download berita dari situs http://www.google.com dapat lebih terstruktur sehingga untuk mendapatkan informasi lebih cepat dan relevan sesuai dengan yang diinginkan.

Academic data increases every year in line with the increase of students. Abundant data store is alsoan abundance of information. Data mining technology is a tool for extracting information on largedatabases and has been widely used in many domains. Predicting student performance (study evaluation) isan activity to determine a future state based on existing data. Data in the field of academic research hasbeen done with various methods and algorithms, but the use of algorithm SLIQ (Supervised Learning InQuest) has not been done.SLIQ is an algorithm developed by the IBM's Quest project team in 1996 for mining large datasets.SLIQ algorithm classify and predict the students performance, beginning with the data cleaning, conductedelection training and testing data. By calculating gini index of each attribute and then selecting thesmallest gini index data table is split according to the criteria until find the same class. From the results ofthe calculation process can produce a set of rules that can be used to predict student performance.From the experiment it can be concluded that the algorithm SLIQ with decision tree technique canbe used as an alternative in designing a system datamining applications. Tests conducted system showedthat the constructed model can be used to predict the performance of new students. The resulting accuracyof the model system in fact has a lower score than the accuracy of other applications that are used as acomparison of Tanagra. Advantages of the proposed system is in its design does not need complexcalculations in obtaining the gini index attributes.

Guna lebih meningkatkan pemahaman dan penguasaan materi yang berkenaan dengan penggunaan sotfware desain grafis, dalam menunjang pembuatan karya-karya desain grafis yang berbobotdan mempunyai nilai jual tinggi diperlukan suatu media yang mampu menyampaikan informasi yang mudah dipahami. Salah satu media informasi yang paling elektif adalah media visual dengan komputer base training dalam bentuk VCD yang dijalankan diatas perangkat komputer, dengan konsep multimedia,informasi yang ditampilkan secara efektif dan atraktif, sehingga penyerapan informasi oleh pengguna menjadi lebih baik. Permasalahan yang perlu diperhatikan : Capture desktop dan pengolahan video danPenggabungan hasil capture yang berupa animasi terpisah satu dengan yang lain. Menggunakan metodeprototyping untuk mendapatkan hasil yang maksimal, sesuai dengan kebutuhan pengguna. Dihasilkanperangkat lunak yang a) memberikan fasilitas auto run agar ketika CD di masukan kedalam CD room bisalangsung terbaca dan keluar dalam tampilan monitor. b) dilengkapi dengan cara penggunaan CD tutorial iniyang berupa tutorial dengan animasi dan ada suaranya agar mudah dipahami.c) dalam penggunaan CDtutorial ini tidak memerlukan software khusus untuk menjalankannya.