Claim Missing Document
Check
Articles

Found 5 Documents
Search

Penerapan K-Means Clustering Untuk Pengelompokan Modalitas Pencitraan Medis Pada Dataset Imaging Data Commons Dea Anggraini; Angelina S. Saragih; Bicanro Gebriyan Panjaitan
International Research on Big-Data and Computer Technology: I-Robot Vol 10, No 1 (2026): April
Publisher : UNIVERSITAS DHARMA WACANA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53514/ir.v10i1.725

Abstract

Distribusi modalitas pencitraan medis dalam dataset Imaging Data Commons (IDC) yang berskala petabyte belum pernah dianalisis secara sistematis menggunakan pendekatan data mining, padahal ketimpangan distribusinya berpotensi memengaruhi kualitas pengembangan model kecerdasan buatan di bidang onkologi. Penelitian ini bertujuan mengelompokkan modalitas pencitraan medis berdasarkan karakteristik distribusi data menggunakan algoritma K-Means Clustering yang diakses melalui Google BigQuery. Data diproses melalui tahapan preprocessing meliputi pembersihan, penyaringan noise, dan normalisasi MinMaxScaler. Nilai K optimal ditentukan melalui Elbow Method menghasilkan K=3. Hasil clustering membentuk tiga kelompok: Cluster 2 (CT, 62,22%), Cluster 1 (MR, 32,41%), dan Cluster 0 (20 modalitas minor, 5,37%), dengan Silhouette Score 0,7823 yang termasuk kategori cluster kuat. Penelitian ini mengungkap bahwa hubungan antara cakupan body part dan volume data bersifat eksponensial, serta dominasi CT dan MRI berpotensi menciptakan blind spot pada model AI medis apabila ketimpangan distribusi tidak ditangani sebelum pelatihan model.
Komparasi Algoritma Dijkstra dan A-Star untuk Optimasi Rute Kendaraan di Kota Medan M. Faris Al Rafiq; Dea Anggraini; Farizky Aulia Lubis; Adidtya Perdana
Jurnal Riset Informatika dan Inovasi Vol 3 No 12 (2026): JRIIN : Jurnal Riset Informatika dan Inovasi (INPRESS)
Publisher : shofanah Media Berkah

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Meningkatnya kebutuhan akan efisiensi mobilitas di kawasan perkotaan menuntut adanya sistem navigasi cerdas yang mampu menentukan jalur perjalanan paling optimal. Penelitian ini mengkaji permasalahan pencarian rute terpendek ( shortest path problem ) dengan membandingkan kinerja komputasi algoritma Dijkstra dan A* (A-Star). Eksperimen dilakukan secara komprehensif pada representasi graf jaringan jalan nyata di Kota Medan (terdiri dari 42.692 node dan 99.736 edge ) yang diekstraksi melalui OpenStreetMap (OSM). Pengujian menggunakan 100 test case yang terstratifikasi dalam kategori jarak dekat, sedang, dan jauh. Hasil penelitian menunjukkan bahwa kedua algoritma secara konsisten menghasilkan jarak rute yang identik, membuktikan bahwa penggunaan heuristik hasrsine pada A* tetap menjamin optimalitas jalur. Namun dari segi efisiensi waktu eksekusi, algoritma A* terbukti jauh lebih unggul dengan memenangkan 95% kasus uji dan mencatatkan rata-rata speedup sebesar 2,83 kali lipat dibandingkan Dijkstra. Analisis lebih lanjut mengungkap bahwa keunggulan waktu komputasi A* memuncak pada rute jarak dekat (3,77x) dan perlahan menurun pada rute jarak jauh (1,68x) akibat kompleksitas topologi jaringan jalan. Berdasarkan uji statistik uji t berpasangan, perbedaan kinerja ini dinyatakan signifikan. Hasil analisis ini diharapkan dapat menjadi rujukan strategi bagi pengembangan sistem transportasi digital, khususnya penyesuaian algoritma perutean pada kondisi topologi lalu lintas riil di Indonesia.
Analisis Perbandingan Kinerja Model Peringkasan Teks Ekstraktif dan Abstraktif (T5, mT5) pada Artikel Berita Berbahasa Indonesia Dea Anggraini; Farizky Aulia Lubis; Callysa Elistia; Azis Kurniadi; Anggia Puteri
Teknik: Jurnal Ilmu Teknik dan Informatika Vol. 6 No. 2 (2026): Oktober: Teknik: Jurnal Ilmu Teknik dan Informatika
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/teknik.v6i2.1254

Abstract

The increasing number of online news articles published every day has created challenges for readers in obtaining important information efficiently. Automatic text summarization offers a solution by generating concise versions of news articles while preserving essential information. This study aims to compare the performance of extractive and abstractive text summarization models for Indonesian-language news articles, namely IndoBERT, T5-Base, and mT5 XL-Sum. The research employed a quantitative experimental approach using the IndoSum dataset, with 200 news articles from the test split selected as evaluation samples. IndoBERT was implemented as an extractive model through binary sequence classification, while T5-Base and mT5 XL-Sum were evaluated using a sequence-to-sequence generative approach. Model performance was measured using ROUGE-1, ROUGE-2, and ROUGE-L metrics to assess information coverage, syntactic quality, and sequence coherence. The results show that T5-Base achieved the highest performance with ROUGE-1 of 0.5686, ROUGE-2 of 0.4950, and ROUGE-L of 0.5365. IndoBERT obtained competitive results with ROUGE-1 of 0.4377, ROUGE-2 of 0.3291, and ROUGE-L of 0.3784, while mT5 XL-Sum produced the lowest scores among the evaluated models. These findings indicate that a monolingual abstractive model specifically trained for Indonesian language tasks is more effective than extractive and multilingual approaches for Indonesian news summarization. The study contributes empirical evidence regarding the suitability of Transformer-based summarization models and can serve as a reference for future development of automatic summarization systems for Indonesian-language content.
Pemodelan Probabilistik Latensi Deteksi Gangguan pada Sistem Monitoring Jaringan Berbasis Polling Menggunakan Simulasi Monte Carlo Dea Anggraini; Zulfahmi Indra; M. Faris Al Rafiq; Qatrunnada Athirah Herdiyanto
Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi Vol. 6 No. 5 (2026): EduTIK : Oktober 2026
Publisher : Jurusan PTIK Universitas Negeri Manado

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67142/edutik.v6i5.647

Abstract

ABSTRAK  Sistem monitoring berbasis polling memeriksa status perangkat secara berkala, sehingga gangguan yang terjadi di antara dua siklus pengecekan baru terdeteksi pada siklus berikutnya. Penelitian terdahulu umumnya melaporkan waktu respons notifikasi, bukan selang waktu sejak gangguan terjadi sampai peringatan pertama tercatat. Penelitian ini memodelkan selang tersebut, yang disebut latensi deteksi, sebagai variabel acak. Data diperoleh dari 40 percobaan terkendali pada router Mikrotik Cloud Hosted Router yang dipantau sistem berbasis Telegram Bot dengan interval pengecekan 30 detik. Analisis meliputi statistik deskriptif, uji Shapiro-Wilk, pencocokan distribusi Normal dengan maximum likelihood, dan uji Kolmogorov-Smirnov dengan koreksi parametric bootstrap. Simulasi Monte Carlo 10.000 iterasi dijalankan dengan pendekatan parametrik dan bootstrap resampling sebagai validasi silang. Latensi deteksi rata-rata 89,688 detik dengan simpangan baku 8,609 detik. Data tidak menyimpang dari distribusi Normal (Shapiro-Wilk p = 0,4093; Kolmogorov-Smirnov terkoreksi p = 0,5487). Peluang latensi melampaui 90 detik sebesar 0,4832 pada pendekatan parametrik dan 0,4863 pada bootstrap. Pada ambang 100 detik hasil keduanya mulai berbeda (0,1125 dan 0,1560), dan pada 120 detik bootstrap tidak dapat menghasilkan nilai di luar rentang data. Nilai terukur lebih dari dua kali perkiraan awal karena lamanya uji ping saat perangkat tidak merespons. Model parametrik lebih layak untuk ekstrapolasi di luar rentang data teramati. Temuan ini terbatas pada satu interval pengecekan dan lingkungan virtual. ABSTRACT  Polling-based monitoring systems check device status at fixed intervals, so a fault occurring between two cycles is only detected in the next one. Earlier studies mostly report notification response time rather than the interval between a fault and the first recorded alert. This study models that interval, called detection latency, as a random variable. Data came from 40 controlled trials on a MikroTik Cloud Hosted Router monitored by a Telegram Bot-based system with a 30-second check interval. The analysis combined descriptive statistics, the Shapiro-Wilk test, maximum likelihood fitting of a Normal distribution, and a Kolmogorov-Smirnov test with parametric bootstrap correction. A Monte Carlo simulation of 10,000 iterations was run with parametric and bootstrap resampling approaches as cross-validation. Mean detection latency was 89.688 seconds with a standard deviation of 8.609 seconds. The data showed no departure from the Normal distribution (Shapiro-Wilk p = 0.4093; corrected Kolmogorov-Smirnov p = 0.5487). The probability of latency exceeding 90 seconds was 0.4832 under the parametric approach and 0.4863 under bootstrap. At 100 seconds the two diverged (0.1125 and 0.1560), and at 120 seconds bootstrap could not produce values beyond the observed range. The measured value was more than twice the initial estimate because of the ping test duration when the device did not respond. The parametric model is better suited to extrapolation beyond the observed range. These findings are limited to a single check interval and a virtual environment.
Monitoring Router Mikrotik CHR Secara Otomatis Menggunakan Telegram Bot Berbasis Python Dea Anggraini; Dedy Kiswanto; Natasha Patricia Nainggolan; Zevan Irfandi Surbakti
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v5i3.556

Abstract

Manual router monitoring is inefficient because network administrators only learn about failures through user complaints rather than automatic system detection. This study aimed to build  an  automated  monitoring  system  for  Mikrotik  CHR  Router  using  a  Python-based Telegram Bot that can detect failures and send automated notifications through periodic monitoring. The system was developed using a prototyping approach and consists of six Python modules running in parallel via threading. Monitoring was performed using the ICMP protocol every 30 seconds, while device information retrieval was done via SSH using the Netmiko library. Testing was conducted through twelve test scenarios simulating router failure using the /disable_interface command through the Telegram bot. The system also includes two network automation features: auto restart interface, which automatically sends the /interface enable command to the router when a failure is detected, and auto backup configuration, which saves the router configuration to a local file each time the router recovers. Test results showed that the failure notification was sent an average of 51 seconds after the interface was disabled in three complete tests. The router was detected as recovered 35 to 44 seconds after the interface was enabled in most events, duplicate alerts were prevented, and 691 log lines were recorded automatically. The results indicate that the system has potential for use in laboratory or small-scale networks.