OBOkky Putra Barus

Okky Putra Barus

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Okky Putra Barus has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Analisis Kualitas Wine Menggunakan Machine Learning dengan Pendekatan SMOTE dan Seleksi Fitur

    by Triandes Sinaga, Kevin Bastian Sirait, Jefri Junifer Pangaribuan, Okky Putra Barus, Romindo Romindo

    Conventional wine quality assessment remains reliant on subjective expert judgment, which introduces potential bias and inconsistency in quality control processes. This study aims to develop an objective and automated machine learning-based classification model to enhance the accuracy of wine quality prediction. To address the issue of class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied, along with ANOVA F-test-based feature selection to optimize model performance. The White Wine Quality dataset from the UCI Machine Learning Repository (4,898 samples, 11 numerical features) was utilized to evaluate five classification algorithms: Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). Before SMOTE application, the Random Forest model achieved an accuracy of only 67.55%. After implementing SMOTE and parameter tuning, the Random Forest (Tuned) model demonstrated the best performance with 90.29% accuracy, 89.99% precision, 90.29% recall, and 89,97%. % F1-score. Additionally, Decision Tree and KNN algorithms also exhibited notable improvements. SMOTE effectively balanced extreme minority class representations (quality levels 3 and 9). The most influential features in quality classification were alcohol content, density, and chlorides. These findings indicate that the proposed framework offers a reliable, objective, and scalable solution for automated wine quality control in industrial production environments.

  • Open Access

    Penerapan Smart Indoor Farming dan Clean Energy Technology untuk Peningkatan Kualitas Produksi Hidroponik

    by Stephanie Stephanie, Jovin Kendrico, Vanesia Roselin, Winar Joko Alexander, Ziven Louis, Okky Putra Barus

    The Global Food Security Index publication notes that Indonesia's food security condition is below the global average. One of the main factors contributing to this issue is climate change and extreme weather. To address this problem, communities can create self-sufficient food sources through home hydroponic farming. Syifa Hidroponik Satu, an MSME in North Sumatra, has been a pioneer in hydroponic plant education and cultivation. However, Syifa Hidroponik Satu faces several production issues, including uncontrolled pests, unpredictable sunlight intensity, high electricity consumption, and inefficient farm monitoring. To overcome these problems, the "Future Farmers" team from Universitas Pelita Harapan implemented smart indoor farming technology and clean energy technology. This technology allows the regulation of temperature, nutrients, pH, and light through an IoT system, and the use of solar panels for energy efficiency. This implementation has successfully improved the quality and productivity of hydroponic farming at Syifa Hidroponik Satu. With these follow-up actions, it is hoped that the quality and productivity of hydroponic farming will continue to increase, making a significant contribution to local food security and supporting greener and more sustainable agriculture.


  • Open Access

    Implementation of the Naive Bayes Algorithm to Predict the Safety of Heart Failure Patients

    by Okky Putra Barus, Kevil Lauwren, Jefri Junifer Pangaribuan, Romindo

    Heart disease stands as a prominent contributor to global mortality, as indicated by data released by the World Health Organization (WHO). In 2019 alone, an estimated 17.9 million individuals succumbed to cardiovascular disease, accounting for 32% of all worldwide deaths. Of these fatalities, 85% were attributed to heart disease and stroke. Individuals harboring the potential for heart failure often persist in unhealthy lifestyles, regardless of their awareness of underlying heart conditions. To address this issue, the research explores the application of machine learning to identify an optimal method for classifying heart failure patients, employing the Naive Bayes technique. This algorithm has found extensive use in the health sector, demonstrating success in classifying various conditions such as hepatitis, stroke, respiratory infections, and more. The Naive Bayes algorithm, applied in this study, exhibited notable accuracy, precision, sensitivity, and overall classification efficacy. Specifically, the classification accuracy for heart failure patients reached 74.58%, the precision level was 97.67%, sensitivity achieved 75%, and the AUC (Area Under ROC Curve) stood at 0.857, indicating excellent classification within the 0.80 to 0.90 range. These findings can serve as an early warning system for individuals at risk of heart failure.


  • Open Access

    Classification of Hearing Loss Degrees with Naive Bayes Algorithm

    by Okky Putra Barus, Romindo, Jefri Junifer Pangaribuan

    According to the World Health Organization (WHO), hearing loss is one of the fourth leading causes of disability. The number of people with hearing loss continues to increase yearly. This increase occurred due to delays in recognizing hearing loss, leading to delays in providing treatment. To solve this problem, one solution to deal with this is early identification to detect the degree of hearing loss. This research will use machine learning to classify the degree of hearing loss. The algorithm implemented in this study is naive Bayes. This study uses a data set from the Zenodo open access repository with 3105 raw data and 19 features. This study evaluates the performance of overall accuracy, precision, recall, and f1-score and classified four classes: mild, moderate, moderately severe, and severe. The methodology classification stages in this study include data preprocessing, data training, data testing, and evaluation. From evaluating the performance of the Naive Bayes algorithm, the classification results obtained the highest impacts in the form of 94% overall accuracy, 100% precision, 100% recall and 97% f1-score in classifying the degree of hearing loss.


  • Open Access

    IMPLEMENTASI ALGORITMA TF-IDF DAN SUPPORT VECTOR MACHINE TERHADAP ANALISIS PENDETEKSI KOMENTAR CYBERBULLYING DI MEDIA SOSIAL TIKTOK

    by Romindo Romindo, Jefri Junifer Pangaribuan, Okky Putra Barus

    Cyberbullying is the act of sending text, images, or videos using the internet, mobile phones, or other devices with the aim of hurting and shaming other people. Cyberbullying is often done through several social media platforms, one of which is through comments on the TikTok application. According to a report by We Are Social, TikTok has 1.4 billion monthly active users aged 18 and above globally. Indonesia currently ranks second in the world in terms of active TikTok users. As a result, the potential for cyberbullying instances will grow as the number of users grows. By using data mining, the public can create a detection system, which can perform analysis on comments in the TikTok application. The method used is Term Frequency-Inverse Document Frequency (TF-IDF) and Support Vector Machine (SVM). The stages passed are to collect comments that are labelled manually. Then, text preprocessing, tokenizing, and weighting were carried out with TF-IDF. Then, implement the Support Vector Machine algorithm to detect cyberbullying comments. This study uses 80% training data and 20% testing data. From the performance results of the Support Vector Machine algorithm, 88% overall accuracy, 88% precision, 96% recall, and 92% f1-score were obtained in detecting cyberbullying comments on social media TikTok.


  • Open Access

    Sosialisasi Sistem Point of Sale Berbasis Web pada Toko Rita Kosmetik

    by Elvina Winarto, Romindo Romindo, Yudhistira Adhitya Pratama, Okky Putra Barus

    Nowadays, cosmetics have become a daily necessity for women, men, and children. The cosmetics in question are not just make-up cosmetics such as powder or blush. Products such as shampoo and soap are also included as cosmetics that fall into the skincare category. Various phenomena or trends that enter Indonesia affect cosmetic sales. Rita Kosmetik Store has been running since 2004 and until now Rita Kosmetik Store is still running its business manually, using paper media. The manual process has many weaknesses, including human error, long data management, weak supervision, and low data integrity. The author then designed a web-based point-of-sale system using Laravel with a MySQL database based on these problems. The resulting point-of-sale system helps Rita Kosmetik Store owners and employees in recording, collecting, and managing business transactions, inventory is properly tracked, and the resulting reports do not take much time and are more accurate.

  • Open Access

    Implementasi Algoritma Support Vector Machine Terhadap Klasifikasi Pose Balet

    by Romindo Romindo, Okky Putra Barus, Jefri Junifer Pangaribuan, Yudhistira Adhitya Pratama, Evelyn Wiliem

    Ballet is considered as one of the most difficult dance due to its technical posture demanded. If performed without guidance it may cause bad posture to ballerina and some serious injuries. A model in identifying different ballet poses is developed with artificial intelligence in order to tear down this barrier. The main purpose of this paper is to demonstrate a methodology that simplified Ballet Pose Recognition using an opensource framework called MediaPipe and a machine learning algorithm called Support Vector Machine. How the model work is it will pass through two stages: first, it extracts data points from an image dataset using the MediaPipe Pose Estimation library, and then it preprocesses the data, trains, validates, and tests it using the Support Vector Machine algorithm to do some pose classification. The model is trained in seven distinct ballet poses, including First Position, Second Position, Third Position, Fourth Position, Fifth Position, Tendu Devant, and Tendu Derrière. This is purposely done in order to assess the competence of the classification model. An accuracy score of 87% is achieved from the ballet pose classification model and is developed to work on images and live videos.


  • Open Access

    Implementasi Filter Augmented Reality pada Usaha Mikro Kecil Menengah untuk Meningkatkan Penjualan

    by Okky Barus, Erick Suliegna, Jefri Junifer Pangaribuan, Jusin Jusin

    Berpindahnya sebuah usaha ke platform digital atau media sosial dapat membantu pelaku usaha untuk menjangkau pemasaran yang lebih luas dalam meningkatkan penjualan. Namun hal ini dapat menjadi tantangan bagi pelaku usaha yang baru memanfaatkan platform ini. Pasalnya, terdapat pelaku usaha lain yang telah lama memanfaatkan media sosial. Sehingga sebuah usaha perlu menerapkan sebuah strategi yang dapat diterapkan melalui platform sosial media tersebut. Salah satu cara untuk meningkatkan penjualan melalui media sosial adalah dengan memanfaatkan filter Augmented Reality. Penelitian ini dilakukan dengan ADDIE Model yakni Analysis, Design, Development, Implementation dan Evaluation. Adapun filter Augmented Reality tersebut dirancang dengan menggunakan tools Spark AR. Dari data metriks filter Augmented Reality yang diperoleh, terdapat 3.434 impressions, 290 captures, 19 saves dan 16 shares. Berdasarkan data penjualan yang diperoleh, terdapat kenaikan sebesar 61% dibandingkan dengan bulan sebelumnya yang belum memanfaatkan filter Augmented Reality. Implementasi filter AR akan tepat jika dilakukan secara musiman atau seasonal.


  • Open Access

    DIGITALISASI PROSES BISNIS PETERNAKAN DENGAN IMPLEMENTASI SISTEM POINT OF SALES (POS)

    by Okky Putra Barus, Jefri Junifer Pangaribuan, Iskandar Muda, Chilwin Chilwin, Ricky Ricky, Sabrina Jovanka, Shendy Dennison, Yudhistira A. Pratama

    One of the problems faced by MSMEs engaged in animal husbandry is the field of business management. Business management is still done traditionally, resulting in a merger of the company's operational funds and the manager's personal funds. This has an impact on the financial statements and the business decision-making process to be wrong. The solution that will be implemented to solve this problem is the digitization of livestock business processes by implementing a point of sales (PoS) system on 786 NS Farm located in Deli Serdang district, North Sumatra province. The implementation of the PoS system can help partners to record transactions digitally, make electronic books and produce financial reports that can assist partners in making decisions in the future. The PoS system implemented is the result of research by the proposing team, namely solutions that have obtained IPR with number No. Registration C00201702295 with the creation title "Officer Mobile Application". The results of this activity are learning the results of six months of mentoring to partners and increasing partner empowerment where partners are able to use the PoS system to record company operational transactions. Salah satu permasalahan yang dihadapi oleh UMKM yang bergerak di bidang peternakan adalah bidang manajemen usaha. Pengelolaan usaha masih dilakukan secara tradisional, sehingga terjadi penggabungan dana operasional perusahaan dan dana pribadi pengelola. Hal ini berdampak kepada laporan keuangan dan proses pengambilan keputusan usaha menjadi keliru. Solusi yang akan diimplementasikan untuk menyelesaikan permasalah ini adalah digitalisasi proses bisnis peternakan dengan implementasi sistem point of sales (PoS) pada peternakan 786 NS Farm yang terletak di kabupaten Deli Serdang provinsi Sumatera Utara. Implementasi sistem PoS dapat membantu mitra untuk mencatat transaksi secara digital, membuat pembukuan elektronik dan menghasilkan laporan keuangan yang dapat membantu mitra dalam mengambil keputusan di masa depan. Sistem PoS yang diimplementasikan merupakan hasil penelitian tim pengusul yaitu solusi yang telah mendapatkan HKI dengan nomor No. Pendaftaran C00201702295 dengan judul ciptaaan “Aplikasi Mobile Perwira”. Adapun hasil capaian kegiatan ini adalah pembelajaran hasil pendampingan selama enam bulan kepada mitra dan peningkatan keberdayaan mitra dimana mitra mampu menggunakan sistem PoS untuk melakukan pencatatan transaksi operasional perusahaan.