Nur holifah, Anggita
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Implementasi Teknologi Deep Learning untuk Diagnostik Stroke Otak Berbasis CNN-LSTM-FNN Nur Holifah, Anggita; Tahyudin, Imam
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 3 (2025): JPTI - Maret 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.538

Abstract

Stroke otak merupakan salah satu penyebab utama kematian dan kecacatan di dunia, dengan dampak besar pada sistem kesehatan dan ekonomi global. Penelitian ini bertujuan untuk mengembangkan model prediksi dini stroke otak berbasis deep learning dengan mengintegrasikan algoritma Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), dan Feedforward Neural Network (FNN). Dataset yang digunakan terdiri atas citra medis seperti CT scan dan MRI, data temporal, serta informasi klinis lainnya, yang diproses menggunakan teknik preprocessing dan augmentasi data. CNN berfungsi untuk mengekstraksi fitur dari citra medis, LSTM untuk menganalisis data sekuensial, dan FNN untuk mengolah data terstruktur. Hasil penelitian menunjukkan bahwa CNN mencapai akurasi tertinggi sebesar 97%, diikuti oleh LSTM dengan 94%, dan FNN sebesar 70%. Integrasi ketiga algoritma ini menghasilkan model prediksi yang lebih akurat dan komprehensif dibandingkan pendekatan individual. Pendekatan ini berpotensi meningkatkan akurasi diagnosis stroke, mempercepat pengambilan keputusan medis, serta mendukung pengelolaan perawatan pasien yang lebih efisien, sehingga dapat mengurangi beban pada sistem kesehatan global.
Analisis Infrastruktur TI Lapak Aduan Banyumas Diskominfo Kabupaten Banyumas Menggunakan SWOT dan Value Chain untuk Evaluasi Layanan Publik Nesa Nur Puspitasari; Nur holifah, Anggita; Retno Setioningrum; Putri Nazilatus Safa’at; Ito Setiawan
Merkurius : Jurnal Riset Sistem Informasi dan Teknik Informatika Vol. 4 No. 1 (2026): Januari : Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/merkurius.v4i1.1377

Abstract

This study aims to explore the condition of information technology infrastructure and to evaluate the extent to which the Lapak Aduan Banyumas service, managed by the Department of Communication and Informatics of Banyumas Regency, operates effectively. The study employs SWOT and Value Chain analysis approaches. A qualitative descriptive method is applied, with data collected through interviews and documentation involving officers responsible for managing the service. The results indicate that Lapak Aduan Banyumas has been operating optimally as a digital-based, transparent, and effective public complaint channel. Its main strengths lie in the ease of access through multiple service channels and the availability of features that enable real-time complaint status tracking. However, several challenges remain, including a limited number of human resources, less optimal collaboration among regional government organizations (OPDs), and network infrastructure constraints in several areas. The Value Chain analysis reveals that the complaint follow-up process and the dissemination of handling outcomes to the public represent the stages that generate the greatest added value in the service process. Therefore, this study suggests strengthening the complaint status monitoring system, enhancing inter-platform service integration, and utilizing artificial intelligence technologies to improve the complaint handling process. The findings of this study are expected to serve as a strategic basis for improving the quality of digital public services in Banyumas Regency.