Claim Missing Document
Check
Articles

Found 35 Documents
Search

Sistem Rekomendasi Pemilihan Jenis Lensa Kacamata Menggunakan Metode Knowledge Based Recommendation (Studi Kasus : Optik Wiratama Kacamata 2) Ulhaq, Ahmad Dia; Hartanti, Dwi; Sari, Aprilisa Arum
STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 10, No 1 (2025)
Publisher : Universitas Indraprasta PGRI Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/string.v10i1.28938

Abstract

The main problem that customers often face in choosing eyeglass lenses is the lack of information that suits the user's specific needs, such as eye complaints, daily activities, and lens feature preferences. This study aims to build a recommendation system for selecting eyeglass lenses using the Knowledge-Based Recommendation approach with the Constraint-Based method. The system development methodology uses the Agile Software Development model, with iterative stages that allow for periodic system evaluation. Data were obtained through interviews with customers and staff of Optik Wiratama Kacamata 2, as well as direct observation of user needs. This system was built web-based with the PHP programming language and the Laravel framework. The system test results showed a level of recommendation accuracy with a recall value of 100% and an average precision of 89.16%, indicating that the system is able to provide relevant lens recommendations that suit user needs. This study contributes to providing digital solutions that help decision-making in selecting eyeglass lenses in a personal and efficient manner.
Pemodelan Sistem Pemilihan Tempat POI Terdekat di Wilayah Klaten Kota Menggunakan Metode Dijkstra oleh PT. Telkom Klaten Erlina Kumala Kusumawati; Dwi Hartanti; Tri Djoko Santosa
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jtik.v9i1.3063

Abstract

The Point of Interest (POI) represents a specific geographic location defined by its coordinates, including longitude and latitude, and holds value as a site of interest or utility. Examples of POIs include tourist attractions, hotels, restaurants, ATMs, pharmacies, health centers, retail shops, gas stations, and other categories integral to modern navigation systems. PT. Telkom Klaten has faced increased demands to conduct POI surveys efficiently, driven by advancements in technology that call for faster and more streamlined processes. A primary challenge in these surveys is the selection of an optimal route that minimizes time, costs, and fuel consumption, given that the company currently relies on manual input in Google Maps to determine distance and travel time. This manual approach may hinder survey efficiency and increase operational costs. To address this, an application employing the Dijkstra algorithm was developed to determine the shortest route effectively. The Dijkstra algorithm, known for selecting edges with minimal weight to connect sequential nodes, requires defined origin and destination points, thereby generating the most efficient route between them. This study applies the Dijkstra algorithm to optimize survey routes by modeling them as graph-based routes, aiming to identify the shortest and most efficient paths between multiple POI locations. The findings indicate that the Dijkstra algorithm significantly reduces travel distance and time, thereby achieving notable savings in fuel and operational time for POI surveys.
Pemodelan Sistem Rekomendasi Pemilihan Paket Internet IndiHome Menggunakan Metode Knowledge Fany Lestari; Dwi Hartanti; Herliyani Hasanah
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 9 No 1 (2025): JANUARI-MARET 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jtik.v9i1.3065

Abstract

As time goes by, the internet has become a basic human need. There are various internet service providers with various and interesting products. Each internet service provider has its own advantages and disadvantages. This makes customers confused about choosing a suitable internet package to use to support their activities. The Indihome internet package selection recommendation system uses a knowledge-based method and is designed to help users choose an internet package that suits their needs. This knowledge based method is based on existing knowledge. The use of a knowledge base is easy for users to understand and makes it possible to produce recommendations that suit user needs. It is hoped that the results of this system can be used as a consideration for consumers in making decisions regarding selecting the internet service package to be used and increasing customer satisfaction.
SEGMENTATION OF SUBARACHNOID HEMORRHAGE ON BRAIN CT IMAGES USING U-NET AND ATTENTION U-NET: A COMPARATIVE ANALYSIS Ilham Tristadika Saputra; Afu Ichsan Pradana; Dwi Hartanti
JIKO (Jurnal Informatika dan Komputer) Vol 8 No 2 (2025)
Publisher : Program Studi Teknik Informatika Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i2.9958

Abstract

Subarachnoid Hemorrhage (SAH) represents a critical medical condition resulting from bleeding in the subarachnoid space, typically due to the rupture of an aneurysm or trauma. Timely identification is vital to avoid long-term neurological impairment. This research assesses the efficacy of U-Net compared to Attention U-Net for the segmentation of SAH in brain CT images, aiming to determine if attention mechanisms enhance segmentation precision. The motivation for this comparison stems from the clinical difficulty in identifying subtle or low-contrast hemorrhagic areas that traditional architectures like U-Net might miss; in contrast, attention-based models are constructed to capture spatial details more proficiently. Both architectures were evaluated using a publicly available SAH CT dataset and assessed on metrics including Dice Score, Intersection over Union (IoU), Precision, Recall, and F1 Score. Attention U-Net outperformed U-Net with higher scores of Dice (0.896) and IoU (0.877), whereas U-Net excelled in precision. Visual assessments also indicated that Attention U-Net was superior in delineating diffuse hemorrhagic regions. These findings advocate for the incorporation of attention mechanisms to enhance segmentation accuracy and clinical relevance in neuroimaging
Komparasi Protokol Transmisi Real-Time Video Streaming pada Drone Quadcopter untuk Monitoring Kegiatan Humas Polri Juantino Brata Astungkara; Afu Ichan Pradana; Dwi Hartanti
Sains Data Jurnal Studi Matematika dan Teknologi Vol 4, No 2: July-December 2026 (In Progress)
Publisher : Institut Nurul Islam Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52620/sainsdata.v4i2.378

Abstract

Perkembangan teknologi Unmanned Aerial Vehicle (UAV) berbasis Internet of Things (IoT) telah membuka peluang baru dalam sistem monitoring real-time, khususnya pada kegiatan dokumentasi dan pengawasan oleh Humas POLRI. Namun, tantangan utama yang dihadapi adalah belum optimalnya transmisi video streaming real-time akibat keterbatasan bandwidth, latency, serta stabilitas jaringan. Penelitian ini bertujuan untuk membandingkan performa protokol komunikasi Message Queuing Telemetry Transport (MQTT) dan Real Time Streaming Protocol (RTSP) dalam mendukung sistem transmisi video pada drone quadcopter berbasis IoT. Metode penelitian yang digunakan adalah eksperimental komparatif dengan pendekatan System Development Life Cycle (SDLC), meliputi analisis kebutuhan, perancangan arsitektur sistem, implementasi, dan evaluasi performa. Parameter yang digunakan dalam pengujian meliputi latency, throughput, jitter, dan packet loss. Hasil penelitian menunjukkan bahwa MQTT memiliki keunggulan dalam stabilitas komunikasi, efisiensi bandwidth, dan tingkat packet loss yang rendah, sehingga lebih cocok untuk kondisi jaringan tidak stabil dan pengiriman data telemetri. Sementara itu, RTSP memiliki performa lebih baik dalam hal latency rendah dan throughput tinggi sehingga lebih optimal untuk kebutuhan video streaming real-time. Kesimpulannya, kedua protokol memiliki karakteristik yang saling melengkapi sehingga pendekatan hybrid direkomendasikan untuk sistem monitoring UAV pada kegiatan Humas POLRI agar mampu menyeimbangkan kualitas video dan keandalan komunikasi data.