cover
Contact Name
PPPM ITPA
Contact Email
sttplppm@gmail.com
Phone
+6285797169678
Journal Mail Official
sttplppm@gmail.com
Editorial Address
Jln. Masik Siagim NO.75 Simpang Mbacang Kel. Karang Dalo
Location
Kota pagar alam,
Sumatera selatan
INDONESIA
Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer
ISSN : 23391871     EISSN : 27157369     DOI : https://doi.org/10.36050/betrik.v10i03
Core Subject : Science,
Besemah Teknologi Informasi dan Komputer (BETRIK) is a national journal published by Pusat Penelitian dan Pengabdian kepada Masyarakat (P3M), Institut Teknologi Pagar Alam (ITPA). This scientific work was published in 3 editions, with topics related to Computers, Technology, and Science. Topics related to this field can be information systems, informatics, computer science, IT business, IT Governance, enterprise architecture planning, software engineering, modeling and simulation, Data Mining, Artificial Neural Network, Digital Image Processing, Algorithm and Programming, Internet of Things (IoT), artificial intelligence, information security, social networking, cloud computing, science, engineering and related topics. The Scientific Journal BETRIK is a peer journal -National review dedicated to the exchange of high-quality research results in all aspects of education and teaching. This journal publishes the latest works in basic theory, experiments and simulations, as well as applications, with systematically proposed methods, adequate reviews of previous works, extended discussions and conclusions. As our commitment to the advancement of education and teaching, the BETRIK Journal follows an open access policy that allows published articles to be available online for free without subscribing.
Articles 239 Documents
Klasifikasi Indikasi Penyakit Jantung Pada Manusia Menggunakan Algoritma Fuzzy KNN Kgs. M. Ammar Yazid; Dedy Hermanto
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/dv8p2p83

Abstract

The high mortality rate from heart disease in Indonesia is largely caused by delayed diagnosis, which stems from low public awareness regarding early screenings. Limited access to accurate health information exacerbates this situation, creating a critical gap between disease onset and medical intervention. This research proposes the development of a classification model for the early detection of heart disease using the Fuzzy K-Nearest Neighbor (Fuzzy KNN) algorithm. This method was chosen for its ability to indicate whether an individual has heart disease and to manage the uncertainty within symptom data, aiming to provide an initial recommendation that can increase public awareness. The model's performance was rigorously evaluated using k-fold cross-validation to ensure valid results. The findings show a significant trade-off. At a k-value of 9, the model achieved a recall of 0.64. However, this was accompanied by a precision of 0.23 and an average accuracy of approximately 0.75. Nevertheless, Fuzzy KNN shows significant potential as an early detection tool due to its strong capability in minimizing the risk of missed patients (false negatives).
Prediksi Emisi Co2  Di Indonesia Menggunakan Pendekatan Hybrid Arima Dan LSTM Syarifuddin Elmi; Rini Yanti; Mardainis; Hadi asnal
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/vtjtfp90

Abstract

Climate change has emerged as a pressing global issue, with carbon dioxide (CO2) emissions serving as a major contributor to global warming. In Indonesia, the expansion of industrial activities, transportation, and the reliance on fossil fuel-based energy have significantly accelerated CO2 emission levels. In this context, the need for accurate emission forecasting has become increasingly important as a basis for formulating data-driven mitigation policies. This study aims to develop a predictive model for CO2 emissions in Indonesia using a hybrid approach that combines AutoRegressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) methods. ARIMA is employed to capture linear patterns in historical time series data, while LSTM is used to model the non-linear and complex dynamics often present in environmental data. The emission data used spans from 1970 to 2023, with training and testing data separated chronologically in an 80:20 ratio. The evaluation results show that the ARIMA model alone yielded suboptimal performance (RMSE: 2342.5139, MAE: 2341.5775, MAPE: 414.77%), whereas the LSTM model significantly improved prediction accuracy (RMSE: 49.3307, MAE: 45.5498, MAPE: 7.94%). The hybrid ARIMALSTM model achieved the best results, with an RMSE of 31.5778, MAE of 25.0335, and MAPE of 4.34%. These findings indicate that the combination of both methods substantially enhances prediction performance compared to standalone models. The implications of this research are twofold: academically, it contributes to methodological development in environmental data analysis; practically, it offers valuable insights for policymakers in formulating more effective and sustainable carbon emission reduction strategies in Indonesia. 
Aplikasi Pendukung keputusan Penerima Beasiswa CSR Menggunakan Weight Product (WP) Bunga Intan; Muhammad Irvai; Nolan Efranda
BETRIK Vol. 14 No. 01 (2023): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/cqe48e24

Abstract

The problem with this research is that in the process of selecting CSR scholarship recipients it is still done manually by filling out the exam sheets that have been provided, then the marketing unit returns to manually record the value data. Applications created using the codeigniter framework programming language are integrated with the Weight Product (WP) method and MySQL Improved as database management. The life flow model used in making this application is the waterfall method. With an online-based Corporate Social Responsibility (CSR) scholarship decision support application, it can support decision making regarding acceptance of CSR scholarships by Bina Insan University. The purpose of this application is to make it easier to manage data on prospective scholarship recipients and make it easier to make decisions so that they are faster, accurate and transparent
Vader Meets Multilingual Voices: Klasifikasi Sentimen Ulasan Pada Aplikasi Babble Dengan Bantuan Deep Translator Yustida Bellini; Ayu Okta Pratiwi
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/fwyg7r05

Abstract

 The rapid advancement of technology today greatly facilitates our access to information—within seconds, we can obtain whatever information we need. This also makes it easier to learn various languages around the world, as seen in the Babbel application. This study aims to identify sentiment in user reviews of the Babbel app by utilizing a combination of Deep Translator, VADER (Valence Aware Dictionary and Sentiment Reasoner), and Logistic Regression. User reviews were collected from the Google Play Store, resulting in 1,000 multilingual reviews. All reviews in different languages were translated into English using Deep Translator. After translation, sentiment labeling was performed using VADER. Then, the text data were transformed into numerical form using TF-IDF vectorization. After all these steps, the classification process was carried out using a Machine Learning model, namely Logistic Regression. The evaluation phase used a Confusion Matrix, and the sentiment classification achieved an accuracy of 89%. This study concludes that the combination of lexical-based analysis and machine learning can provide reliable results for multilingual sentiment analysis. In the future, this approach can be further developed by evaluating the performance of other classification algorithms.
Implementasi Algoritma K-Means Untuk Mengetahui Faktor Penyebab Perceraian Siti Muntari; Sasmita; Weny Pebrianti
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/ep1sxt09

Abstract

This research aims to analyze the factors causing divorce in the city of Pagar Alam using the K-Means Clustering algorithm. Divorce data from the year 2020 to 2024 was obtained from the Religious Court. Divorce cases in the last five years show fluctuating trends influenced by several factors. Data collection methods were conducted through observation, interviews, literature studies, and documentation. This research adopts the KMeans algorithm with the CRISP-DM method, going through the stages of Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The tools used are Google Colab with Silhouette Score testing. The research results show three clusters: C0 high with 286 cases (ongoing disputes), C1 medium with 337 cases (economic factors), and C2 low with 494 cases (loss of one party). The optimal cluster value k = 3 was obtained from the Elbow Method, with a Silhouette Score of 0.37
Implementasi Algoritma Regresi Linear Untuk Memprediksi Harga Laptop Risky Harahap; Karpen,; Helda Yenni; Muhamad Jamaris
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/rnnp7x70

Abstract

The development of laptop technology has driven the need for accurate price predictions to assist consumers in making purchasing decisions appropriately and efficiently. This study implements a Linear Regression algorithm to predict laptop prices based on 4 main features including Brand, Processor, RAM, and GPU. The dataset used consists of 11,768 data obtained from the Kaggle platform which is processed through preprocessing, feature transformation, and model evaluation stages with various performance metrics. The analysis results show that the RAM feature has the most significant influence on laptop prices, followed by Processor, Brand, and GPU. The developed Linear Regression model successfully achieved an R-squared value of 0.6453, which indicates that the model is able to explain 64.53% of the variation in laptop prices based on the analyzed features. This study contributes to the development of an accurate laptop price prediction system and provides a practical tool to support data-based purchasing decisions effectively and efficiently.
Implementasi Sistem Hotspot Menggunakan Mikrotik Dan Captive Portal Sebagai Media Penunjang Aktivitas Belajar Hairil Novansyah; Sigit Candra Setya
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/4er7dd06

Abstract

The need for internet access on campus is increasing, particularly for searching and utilizing information to support the teaching and learning process. At the Pagar Alam Institute of Technology, the current hotspot network is limited to certain rooms, such as the STAFF, LPPM, BAAK, and Multimedia Laboratory, making it difficult for all students to access it equally. This situation results in limited access to information and hinders the learning process. This research aims to design and implement a dedicated student hotspot network to expand internet access on campus. The PPDIOO (Prepare, Planning, Design, Implement, Operate, Optimize) method is used, supported by Unified Modeling Language (UML)-based system modeling tools, such as use case diagrams and activity diagrams. The Queue Tree method is used to manage and distribute bandwidth. The result of this research is a hotspot network accessible to students on campus, with a bandwidth of 512 Kbps per user. This network supports various learning activities, such as browsing, access to the SPADA and SISTA systems, and other online learning services like YouTube This implementation is expected to support the academic process and improve the quality of learning at the Pagar Alam Institute of Technology.
Penerapan KNN, DT, dan NB untuk Memprediksi Task Success Developer Berbasis AI-Metrics Iski Mediansyah; Muhammad Bitrayoga; Arief Zikry; Firza Septian
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/rsvfdr22

Abstract

This study is motivated by the limited utilization of AI-based metrics to predict task success among developers in software development projects. The main issue addressed is the absence of a systematic comparative approach to classification algorithms in identifying the most effective model in this context. Therefore, this research compares the performance of three classification algorithms—K-Nearest Neighbors (KNN), Decision Tree (DT), and Naïve Bayes (NB)—in predicting task success using AI-metrics data. The evaluation metrics include precision, recall, F1-score, and accuracy, presented through classification reports and confusion matrices. The results show that DT achieved an accuracy of 91%, KNN 92%, and NB 86%. The confusion matrix analysis indicates that DT demonstrates high precision, KNN shows minor imbalance, and NB struggles to identify minority classes. Additionally, clustering was performed using the K-Means algorithm and visualized in two dimensions through Principal Component Analysis (PCA),  revealing clear segmentation among developer groups. The ultimate benefit of this study is to provide a foundation for decision-making in selecting the most appropriate algorithm to enhance developer team effectiveness and personalize managerial strategies. The novelty of this research lies in the combined application of classification and clustering approaches using AI-metrics to more accurately and datadrivenly identify developer task success. 
Perancangan Sistem Informasi E-Arsip Dokumen Berbasis Codeigneter Pada Divisi Pertanahan Di PT. Deltacendana Citapersada Puput Julyanti; Sigit Auliana; Basuki Rakhim Setya Permana
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/kxftyj47

Abstract

The development of information technology has encouraged organizations to shift from conventional archive management systems to more efficient and integrated digital systems. PT. Deltacendana Citapersada, particularly in the Land Division, still faces obstacles in manually managing important document archives, such as the risk of data loss, slow searches, and lack of access control. This study aims to design and develop a web-based document e-archive information system using the CodeIgniter framework to improve the effectiveness and efficiency of the archiving process. This study uses a descriptive method with a field study approach through observation and interviews. System development is carried out using the Waterfall model, through the stages of needs analysis, system design, interface implementation, and testing. The system built includes role-based login features, category management, multi-format document uploads, archive searches, and user management. Testing results using the black box method show that all system functions run according to specifications, and User Acceptance Testing (UAT) testing shows a user satisfaction level of 89.47%, which indicates the system is well received. This study concludes that the designed e-archive system has successfully replaced conventional archiving methods with a more efficient and structured e-archive system. This transition overcomes various problems in manual archiving, such as the difficulty of searching for documents, the risk of archive loss, and the potential for document damage due to human error or environmental factors. Therefore, the developed digital system is deemed feasible for implementation as a modern and reliable archive management solution. For further development, it is recommended to add notification features, integrate with cloud storage services, and provide user training to maximize system utilization. 
Model Prediksi Jumlah Produksi Kelapa Sawit Menggunakan Regresi Linear Berganda di PT.Surya Argolika Reksa Irpan M irpan; Unang Rio; Karpen; Hamdani
BETRIK Vol. 16 No. 02 (2025): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/dv9sd116

Abstract

Palm oil plantations are one of the strategic sectors in Indonesia’s agribusiness industry. To support production efficiency and effectiveness, a predictive model capable of accurately estimating production volume based on supporting factors is required. This study aims to develop a prediction model for palm oil production using the Multiple Linear Regression algorithm by utilizing variables such as land area (Ha), number of trees, and rainfall. The data were obtained from the operational reports of PT. Surya Argolika Reksa. The model evaluation was conducted using two data splitting scenarios: 80:20 and 70:30. The evaluation results show that for the 80:20 test data, the MAE value was 30,095.68, the MSE was 1,533,325,063.46, and the RMSE was 39,151.33. Meanwhile, for the 70:30 test data, the MAE value was 35,455.01, the MSE was 2,096,902,404.44, and the RMSE was 45,791.95. These values indicate the level of prediction error of the model in units of palm oil production. This research contributes to supporting more accurate production planning in the palm oil plantation sector based on data analysis.