Claim Missing Document
Check
Articles

Found 25 Documents
Search

Analisis Performa Metode Machine Learning dalam Mengidentifikasi Penyebab Ulasan Rating Satu Aplikasi MyBluebird Azziizah, Almira Farradinda; Mustofa, Hery; Umam, Khothibul; Handayani, Maya Rini
Jurnal Ilmiah Global Education Vol. 6 No. 4 (2025): JURNAL ILMIAH GLOBAL EDUCATION
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/jige.v6i4.4704

Abstract

This study addresses the increasing prevalence of negative user reviews for the MyBluebird ride-hailing application, focusing on the identification and classification of the main causes of one-star ratings. The research aims to compare the effectiveness of Support Vector Machine, Random Forest, and Naïve Bayes algorithms in classifying user complaints. Employing a quantitative experimental approach, the study utilizes a dataset of 1,399 one-star reviews collected purposively from Google Play Store. Data preprocessing includes cleaning, tokenization, and feature extraction using TF-IDF. The classification models are evaluated using accuracy, precision, recall, and F1-score metrics. Results indicate that Random Forest achieves the highest accuracy (90%), outperforming the other algorithms, with bugs/errors as the most frequent complaint, followed by driver performance, other issues, and price. The study concludes that machine learning-based classification can effectively map user dissatisfaction, though data imbalance remains a limitation. Future research should apply data balancing techniques and expand the dataset for broader generalization. Practical implications suggest that developers can utilize automated classification to improve service quality and address user needs more efficient.
Analisis Forensik Metadata Lokasi Android Dengan Autopsy dan Evaluai Akurasi Haversine Nuurun Najmi Qonita; Divana Taricha Salmalina; Danita Divka Sajmira; Hery Mustofa
Cyber Security dan Forensik Digital Vol. 8 No. 2 (2025): Edisi November 2025
Publisher : Fakultas Sains dan Teknologi UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/csecurity.2025.8.2.5221

Abstract

Di balik setiap foto yang diambil dengan ponsel Android tersembunyi jejak digital yang tak kasat mata yaitu metadata lokasi. Informasi ini bukan sekadar angka koordinat, melainkan kunci penting dalam menelusuri perjalanan seseorang dalam investigasi forensik digital. Penelitian ini bertujuan untuk menganalisis metadata lokasi dari citra Android menggunakan perangkat lunak forensik open-source Autopsy, serta mengevaluasi akurasi data lokasi tersebut dengan rumus Haversine. Metode yang digunakan meliputi ekstraksi metadata EXIF dari file gambar, pengumpulan koordinat lokasi sebenarnya sebagai ground truth, dan penghitungan jarak kesalahan posisi. Hasil menunjukkan bahwa Autopsy mampu mengidentifikasi metadata lokasi dengan rata-rata tingkat akurasi sebesar 0.30 meter, yang menjadikannya alat yang dapat diandalkan dalam mendukung proses investigasi forensik digital. Kata kunci: Forensik Digital, Metadata Lokasi, Android, EXIF, Autopsy -------------------------------------------------------------------------------------------------- FORENSIC ANALYSIS OF ANDROID LOCATION METADATA USING AUTOPSY AND HAVERSINE ACCURACY EVALUATION Behind every photo taken with an Android phone lies an invisible digital trace, location metadata. This information is more than just a set of coordinates; it can serve as a crucial key in uncovering an individual's movements during a digital forensic investigation. This study aims to analyze the location metadata embedded in Android images using the open-source forensic tool Autopsy, and to evaluate the accuracy of the retrieved location data using the Haversine formula. The methodology involves extracting EXIF metadata from image files, collecting the actual location coordinates as ground truth, and calculating the positional error distance. The results show that Autopsy is capable of identifying location metadata with an average accuracy of 0.30 meters, making it a reliable tool to support digital forensic investigations. Keywords: Digital Forensics, Location Metadata, Android, EXIF, Autopsy
Analisis komparatif kinerja HAProxy dan Zevenet pada infrastruktur web server Bare-Metal Linux Nursafaat, Maulachusnan; Mustofa, Hery; Yuniarti, Wenty Dwi; Umam, Khothibul
AITI Vol 23 No 1 (2026)
Publisher : Fakultas Teknologi Informasi Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/aiti.v23i1.106-116

Abstract

As systems demand high speed, stability, and the ability to handle large volumes of traffic, selecting an appropriate load-balancing solution becomes a critical aspect of infrastructure design. This study aims to compare the performance of two open-source load balancers, HAProxy and Zevenet, implemented on a Linux-based bare-metal web server infrastructure. The experiment was conducted using two identical backend servers and the wrk benchmarking tool, configured for five-minute tests, 1000 concurrent connections, and twelve repetitions per platform. The evaluation metrics included average latency, request throughput, and the number of timeout errors during the testing period. The results show that HAProxy achieved lower average latency (261.97 ms), higher throughput (1076.68 RPS), and fewer timeout errors (37,742) than Zevenet. While Zevenet offers a more user-friendly graphical interface, HAProxy proved more efficient and stable under high traffic. This study provides practical insights for implementing effective load balancing in non-virtualized systems with limited resources and high-performance demands.
TINGKAT KEMATANGAN TATA KELOLA TEKNOLOGI INFORMASI MENGGUNAKAN METODE TESCA Hery Mustofa; Syaiful Bakhri
JSAI (Journal Scientific and Applied Informatics) Vol 3 No 3 (2020): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v3i3.1159

Abstract

Evaluasi tata kelola TIK menjadi bagian penting dalam penerapan TIK dalam sebuah perguruan tinggi. Tata kelola teknologi informasi yang baik akan membantu mempercepat terwujudnya visi dan misi sebuah perguruan tinggi. Pusat Teknologi Informasi dan Pangkalan Data (PTIPD) UIN Walisongo merupakan unit teknis yang  mempunyai tugas mengelola dan mengembangkan sistem informasi di lingkungan Institusi. Mengingat pentingnya PTIPD maka perlu dilakukan evaluasi tingkat kematangan teknologi informasi dengan menggunakan metode TeSCA. Analisis dilakukan dengan teknik observasi, wawancara, penelaah dokumen dan konfirmasi untuk mendukung analisis terhadap PTIPD. Hasil analisis menunjukkan bahwa tingkat kematangan TIK UIN Walisongo pada tingkat Level Madya dengan scores total 55.43.
Analysis of NGINX Static Content Delivery on the Performance of a Docker-based Photo Gallery Backend Itsna Nur Hamida; Masy Ari Ulinuha; Hery Mustofa; Khothibul Umam
Sistemasi: Jurnal Sistem Informasi Vol 15, No 4 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i4.6139

Abstract

Photo studio websites typically present large volumes of multimedia content through photo gallery modules. In many implementations, this content is served dynamically by the application backend, which can increase processing load and degrade system performance. This study analyzes the impact of static content delivery using NGINX on the performance of a Docker-based photo gallery backend. A quantitative experimental method was applied by comparing two scenarios: dynamic content delivery without NGINX and static content delivery using NGINX. The experiments were conducted using Apache Benchmark with identical request and concurrency parameters, accompanied by monitoring of backend resource utilization. The results show that dynamic delivery produces lower throughput (463.78 requests per second) and higher response time (108.27 ms), along with significant backend CPU usage. In contrast, the use of NGINX increases throughput to 1105.25 requests per second, reduces response time to 45.33 ms, and significantly lowers backend CPU and memory consumption. These findings demonstrate that separating static and dynamic content delivery using NGINX is effective in improving backend performance in Docker-based photo gallery applications.