Claim Missing Document
Check
Articles

Found 6 Documents
Search

Visualisasi Organ Tubuh Dampak Merokok Menggunakan Augmented Reality Purnamasari, Fanindia; Huzaifa, Ade Sarah; Ayura, Dhaffa Safira
JTIM : Jurnal Teknologi Informasi dan Multimedia Vol. 7 No. 2 (2025): May
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v7i2.590

Abstract

Cigarettes are an addictive substance that can cause addiction for those who consume them. Each cigarette contains more than 4,000 types of harmful chemicals for the body. However, smoking has become a habit for some people, especially men, it can harm health and become a source of disease. One of these diseases is coronary heart disease and lung cancer, which are among the leading causes of death due to smoking annually. In 2019, Indonesia had the highest number of teenage smokers in ASEAN, therefore the importance of education about the dangers of smoking is highlight. Public service announcements are a common form of education about the dangers of smoking. According to data, 51.10% of the Indonesian population are active smokers, the highest rate in ASEAN. Raising awareness about the health hazards of smoking, especially to the heart and lungs is crucial and should be conveyed to the public through educational, informative, and interactive media. One such method is the use of multimedia with augmented reality technology. Augmented reality is a technology that can project a 3Dimensional (3D) object into the real world in real-time. This research implements augmented reality using a markerless approach that can display 3D objects of human organs, such as the lungs and heart, affected by smoking.
Enhancing Single Nucleotide Polymorphisms Detection from Imbalanced Data: A Study of Resampling Techniques in Machine Learning Algorithms Nurhasanah, Rossy; Arisandi, Dedy; Purnamasari, Fanindia; Hayatunnufus, Hayatunnufus; Simangunsong, Daisy Sere Damara; Pulungan, Aflah Mutsanni
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.32942

Abstract

Identifying the actual Single Nucleotide Polymorphisms (SNPs) by sourcing Next Generation Sequencing (NGS) data emerges an imbalanced problem due to the inherent high error rate of NGS technology. The imbalance problem has been found to have a negative impact on machine learning algorithms because it produces biased models and poor performance, particularly in detecting actual SNP that belong to the underrepresented class in question.   This study evaluates the effectiveness of several resampling techniques, including Borderline-SMOTE, Random Undersampling, and Tomek-Link, in enhancing the performance of machine learning algorithms, specifically Random Forest (RF) and Artificial Neural Networks (ANN). Furthermore, we compare these techniques to determine the most effective approach. Our results indicate that Borderline-SMOTE improves the F-Measure of RF from 69.72 to 91.52 (a 31.2% increase) and ANN from 79.75 to 91.32 (a 14.5% increase) and outperforms other resampling methods. These findings highlight the crucial role of resampling techniques and the careful selection of algorithms in improving classification accuracy for imbalanced datasets.
PENDEKATAN DATA-DRIVEN: CLUSTERING UNTUK SEGMENTASI KARYAWAN YANG CENDERUNG MENGALAMI ATRISI Purnamasari, Fanindia
Djtechno: Jurnal Teknologi Informasi Vol 6, No 2 (2025): Agustus
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v6i2.6676

Abstract

Analisis sumber daya manusia dapat dilakukan melalui pendekatan berbasis data untuk mendukung pengambilan keputusan yang lebih efektif. Clustering, yaitu metode pengelompokan data berdasarkan kesamaan fitur tanpa label sebelumnya, merupakan salah satu teknik yang banyak digunakan. Penelitian ini bertujuan untuk menemukan pola dan mengklasifikasikan kelompok karyawan yang berpotensi mengalami atrisi berdasarkan karakteristik seperti performa kerja, masa kerja, dan data demografis. Dua algoritma clustering, yaitu K-Means dan DBSCAN, dibandingkan untuk mendapatkan hasil terbaik. Hasil penelitian menunjukkan adanya empat kelompok utama: pekerja senior dengan performa tinggi, karyawan dengan pengalaman baru, tenaga teknis berpengalaman, dan kelompok produktif dengan latar belakang pengalaman yang beragam. Proses prapemrosesan, analisis data, dan penerapan algoritma clustering dilakukan untuk menghasilkan segmentasi yang akurat. Hasil segmentasi ini diharapkan dapat menjadi dasar bagi manajemen dalam merancang strategi pengembangan SDM yang lebih tepat sasaran, serta meningkatkan efisiensi dan perencanaan SDM secara keseluruhan.  
Enhancing marketing efficiency through data-driven customer segmentation with machine learning approaches Purnamasari, Fanindia; Putri Nasution, Umaya Ramadhani M. O.; Elveny, Marischa
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i2.pp1399-1410

Abstract

The importance of understanding consumer behavior in transaction data has become a key to improving marketing efficiency. This study aims to explore the application of machine learning (ML) techniques for data-driven consumer segmentation, focusing on improving product marketing strategies. This work addresses the limitations in the existing literature, especially in terms of handling high-dimensional data that can reduce segmentation quality. Previously, various studies have used clustering algorithms such as K-means without considering dimensionality reduction, which often leads to decreased accuracy and long computation time. In this study, we propose a new approach that combines principal component analysis (PCA) for dimensionality reduction and K-means clustering for consumer segmentation based on purchasing behavior. Experimental results show that using PCA to reduce data dimensionality significantly improves segmentation quality with an inertia score of 1,455,650 and a silhouette score of 0.486366. By implementing this method, we can group consumers into three segments based on frequently purchased product categories and the most common payment methods. These findings provide a scalable, data-driven segmentation framework that can be applied to improve marketing effectiveness by providing special discounts on various products based on the payment method used.
Implementation of Web Based E-Monitoring for Student Activities Record in SMK Swasta Medan Area 1 Hizriadi, Ainul; Nasution, Umaya Ramadhani Putri; Purnamasari, Fanindia
ABDIMAS TALENTA: Jurnal Pengabdian Kepada Masyarakat Vol. 8 No. 2 (2023): ABDIMAS TALENTA: Jurnal Pengabdian Kepada Masyarakat
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/abdimastalenta.v8i2.11192

Abstract

SMK Medan Area 1 is one of the educational facilities that want to produce the best students to be able to become the best human resources in the future. The school is one of the secondary schools located in the city of Medan, North Sumatra province. The school provides various educational support facilities for its students so that they can learn to the fullest. For the sake of education progress, this Medan Area 1 Vocational School wants to take advantage of the available facilities and infrastructure, one of which is the internet. The school's need to quickly and easily supervise student activities and the curiosity of parents/guardians for information related to their sons and daughters makes a new need to continue to be able to unite all their children's activities at the school. These activities include attendance, tuition payments, notification of grades and violations committed by their sons and daughters. Therefore, a web-based monitoring application is needed to unify student activities that can be seen from anywhere, especially by parents/guardians. aims to provide convenience to teachers, especially counseling guidance (BK) teachers and web-based students in unifying several student activities including attendance, tuition payments, value notifications, and the method used in making applications carried out through five stages, namely: development problems , data collection for system requirements, system analysis and design, system implementation and implementation, and system testing
Efisiensi Energi Pada Kinerja Protocol Routing DSDV Berbasis Collision di Wireless Sensor Network Adriansyah, R A Fattah; Huzaifah, Ade Sarah; Hizriadi, Ainul; Purnamasari, Fanindia
Journal Automation Computer Information System Vol. 5 No. 2 (2025): November
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jacis.v5i2.144

Abstract

Wireless Sensor Network (WSN) memiliki kekurangan disamping kelebihannya yang dapat digunakan di lingkungan extreme. Salah satu kekurangan yang menjadi faktor penting pada WSN adalah energi yang terbatas, karena kehabisan daya pada node-node di WSN sebelum menyelesaikan tugasnya akan menjadi masalah. Pada penelitian ini kami mencoba untuk memperpanjang masa pakai WSN yang menggunakan protocol routing DSDV dengan memanfaatkan kejadian yang sangat sulit dihindari pada sistem WSN dengan jumlah node yang banyak, yaitu tabrakan data (collision). Pada kondisi WSN yang menggunakan topologi grid dengan jumlah node 12, 30, dan 70 akan diterapkan protocol routing DSDV yang akan dibandingkan dengan protocol routing DSDV berbasis collision pada kondisi WSN yang sama. Dari beberapa percobaan dengan variasi jumlah node didapatkan hasil jaringan WSN yang menggunakan protocol routing DSDV berbasis collision lebih baik dalam hal pengiriman packet mencapai 92 packet dan efisiensi energi mencapai 10 milijoule