Garuda - Garba Rujukan Digital

Pengembangan Sistem Booking Web Real-Time dengan Kalender Monitoring dan Live Chat Tjahaja79 ardiansyah, bangga aditya; Meimaharani, Rizkysari; Chamid, Ahmad Abdul
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 15, No 1 (2026): Februari 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i1.3493

The manual reservation process at Cafe Tjahaja79 often leads to operational inefficiency and a lack of transparency regarding table availability for customers. This study aims to develop a web-based booking system integrated with a real-time monitoring calendar and live chat to address these issues. The system development method employed is the Waterfall model, ranging from requirements analysis to implementation, while functionality testing was conducted using Black Box Testing. The system is designed to facilitate table reservations, digital payments via QRIS, and instant communication between customers and administrators. The test results indicate that all system features function validly and are free from functional errors. It is concluded that the implementation of this system effectively improves the efficiency of reservation management administration and provides service certainty for customers through accurate schedule visualization.Keywords: Online booking system; Table reservation; Live chat; Digital calendar; Waterfall. AbstrakProses reservasi manual di Cafe Tjahaja79 sering kali menyebabkan ketidakefisienan operasional dan minimnya transparansi informasi ketersediaan meja bagi pelanggan. Penelitian ini bertujuan mengembangkan sistem booking berbasis web yang terintegrasi dengan kalender monitoring real-time dan live chat untuk mengatasi permasalahan tersebut. Metode pengembangan sistem yang diterapkan adalah Waterfall, mulai dari analisis kebutuhan hingga implementasi, sedangkan pengujian fungsionalitas dilakukan menggunakan Black Box Testing. Sistem dirancang untuk memfasilitasi reservasi meja, pembayaran digital via QRIS, serta komunikasi instan antara pelanggan dan admin. Hasil pengujian menunjukkan bahwa seluruh fitur sistem berjalan valid dan bebas dari kesalahan fungsional. Disimpulkan bahwa implementasi sistem ini efektif meningkatkan efisiensi administrasi pengelolaan reservasi serta memberikan kepastian layanan bagi pelanggan melalui visualisasi jadwal yang akurat.

Rancang Bangun Dashboard Monitoring Pengiriman Bermasalah pada E-Commerce marta, amelia vidora revita; riadi, aditya akbar; chamid, ahmad abdul
Progresif: Jurnal Ilmiah Komputer Vol 22, No 1 (2026): Januari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i1.3516

The rapid growth of e-commerce has increased the volume of orders that must be monitored by sellers, making the handling of delivery delays a major challenge. This study designs and develops a dashboard to monitor problematic shipments on an e-commerce platform by applying a Service Level Agreement (SLA) approach as the basis for evaluating delivery delays. The research adopts a Research and Development (R&D) method with the Waterfall system development model, which includes the stages of requirement analysis, system design, implementation, and functional testing. The developed dashboard is able to automatically classify shipment statuses based on SLA calculations, display indicators of orders at risk of delay, and present delivery data through graphical visualizations. The testing results indicate that the system successfully presents real-time delivery data, proactively detects potential delays, and supports sellers in making operational decisions. This system provides a more effective and measurable SLA-based approach for monitoring e-commerce deliveries.Keywords: Monitoring dashboard; Problematic delivery; Service Level Agreement; E-commerce; Automatic detection.AbstrakPerkembangan e-commerce telah meningkatkan volume pesanan yang harus dipantau oleh seller, sehingga penanganan keterlambatan pengiriman menjadi tantangan utama. Penelitian ini merancang dan membangun sebuah dashboard untuk memonitor pengiriman bermasalah pada platform e-commerce dengan pendekatan Service Level Agreement (SLA) sebagai dasar penilaian keterlambatan pengiriman. Metode yang digunakan adalah Research and Development (R&D) dengan model pengembangan sistem Waterfall, yang meliputi tahapan analisis kebutuhan, perancangan sistem, implementasi, dan pengujian fungsionalitas. Dashboard yang dikembangkan mampu mengklasifikasikan status pengiriman secara otomatis berdasarkan perhitungan SLA, menampilkan indikator pesanan berisiko terlambat, serta menyajikan grafik visualisasi pengiriman. Hasil pengujian menunjukkan bahwa sistem berhasil menampilkan data pengiriman secara real-time, mendeteksi potensi keterlambatan secara proaktif, dan membantu seller dalam pengambilan keputusan operasional. Sistem ini memberikan pendekatan monitoring pengiriman yang lebih efektif dan terukur berbasis SLA.Kata kunci: Dashboard monitoring; Pengiriman bermasalah; Service Level Agreement; E-commerce; Deteksi otomatis

CNN-Based Automatic Detection of Corn Leaf Diseases Using Desktop GUI Application Salsabilah, Nisrina Rona; Riadi, Aditya Akbar; Chamid, Ahmad Abdul
Progresif: Jurnal Ilmiah Komputer Vol 22, No 1 (2026): Januari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i1.3501

Early detection of corn leaf diseases plays a crucial role in improving agricultural productivity. This study develops an automatic detection system for corn leaf diseases using a Convolutional Neural Network (CNN) implemented in a desktop-based GUI application. The model was developed using a transfer learning approach with a dataset of 2,400 corn leaf images divided into four classes: Blight, Common Rust, Gray Leaf Spot, and Healthy. The research stages included image preprocessing, model training and evaluation, and implementation of the trained model into an offline desktop application. Experimental results show that the CNN model achieved an accuracy of 90.00%, with precision of 90.02%, recall of 90.00%, and an F1-score of 90.00%. The Healthy class demonstrated the best performance, while the Blight class showed the lowest but remained in a good category. The developed system enables fast, practical, and efficient disease detection and has the potential to support objective early diagnosis in agriculture.Keywords: CNN; Deep Learning; Disease Detection; Corn Leaf; Transfer Learning AbstrakDeteksi dini penyakit daun jagung berperan penting dalam meningkatkan produktivitas pertanian. Penelitian ini mengembangkan sistem deteksi otomatis penyakit daun jagung menggunakan metode Convolutional Neural Network (CNN) berbasis aplikasi GUI desktop. Model dikembangkan dengan pendekatan transfer learning menggunakan 2.400 citra daun jagung yang terbagi dalam empat kelas, yaitu Blight, Common Rust, Gray Leaf Spot, dan Healthy. Tahapan penelitian meliputi preprocessing citra, pelatihan dan evaluasi model, serta implementasi model ke dalam aplikasi desktop yang dapat digunakan tanpa koneksi internet. Hasil pengujian menunjukkan akurasi sebesar 90,00%, precision 90,02%, recall 90,00%, dan F1-score 90,00%. Kelas Healthy memiliki performa terbaik, sedangkan kelas Blight terendah namun tetap dalam kategori baik. Implementasi sistem memungkinkan proses deteksi dilakukan secara cepat, praktis, dan efisien. Sistem yang dikembangkan berpotensi mendukung deteksi penyakit secara objektif serta membantu meningkatkan produktivitas pertanian.Kata kunci: CNN; Deep Learning; Deteksi Penyakit; Daun Jagung; Transfer Learning

Klasifikasi Penulisan Huruf Hijaiyah Menggunakan Algoritma Convolutional Neural Network Pada TPQ I’anatut Tholibin fatmarini, dini; Riadi, Aditya Akbar; Chamid, Ahmad Abdul
Progresif: Jurnal Ilmiah Komputer Vol 22, No 1 (2026): Januari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i1.3531

This research was conducted due to difficulties in recognizing handwritten Hijaiyah letters at TPQ I’anatut Tholibin caused by variations in writing styles and similarities among letters. The study aims to develop a handwritten Hijaiyah letter classification system based on a Convolutional Neural Network (CNN) using the MobileNetV2 architecture. The research employed a Research and Development (R&D) approach, including real-time data collection from students’ handwritten samples, image preprocessing (resizing to 224×224, pixel normalization, and augmentation), model design using transfer learning, training, and testing. Model evaluation was performed using test data that were not involved in the training process, with performance assessed through a confusion matrix and metrics such as accuracy, precision, recall, and F1-score. The experimental results show that the model achieved an accuracy of 78.46% with a macro F1-score of 77.29%, indicating a reasonably good and balanced classification performance across classes. The system was implemented as a web-based application supporting real-time testing through direct writing on a digital canvas, enabling interactive classification. These findings demonstrate that MobileNetV2 is effective for handwritten Hijaiyah letter classification and has potential as an intelligent learning support tool.Keywords: Hijaiyah letters; Convolutional neural network; MobileNetV2; Image classification; Real-time systemAbstrakPenelitian ini dilakukan karena pengenalan tulisan tangan huruf hijaiyah di TPQ I’anatut Tholibin masih terkendala variasi bentuk tulisan dan kemiripan antar huruf. Penelitian ini bertujuan mengembangkan sistem klasifikasi tulisan tangan huruf hijaiyah berbasis Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2. Metode yang digunakan adalah Research and Development (R&D) dengan tahapan pengumpulan data tulisan tangan murid secara real-time, pra-pengolahan citra (resizing 224×224, normalisasi piksel, dan augmentasi), perancangan model dengan pendekatan transfer learning, pelatihan, dan pengujian. Pengujian dilakukan menggunakan data uji yang tidak dilibatkan dalam proses pelatihan, dengan evaluasi performa menggunakan confusion matrix dan metrik akurasi, precision, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model mencapai akurasi sebesar 78,46% dengan nilai macro F1-score 77,29%, yang menandakan performa klasifikasi yang cukup baik dan relatif seimbang antar kelas. Sistem diimplementasikan dalam aplikasi web dengan pengujian real-time melalui penulisan langsung pada kanvas digital sehingga klasifikasi dapat dilakukan secara interaktif. Temuan ini menunjukkan MobileNetV2 efektif untuk klasifikasi huruf hijaiyah tulisan tangan dan berpotensi sebagai alat bantu pembelajaran.Kata Kunci: Huruf hijaiyah; Convolutional neural network; MobileNetV2; Klasifikasi citra; Sistem realtime

Penerapan Algoritma Support Vector Machine Dalam Analisis Sentimen Terhadap Ulasan Pengguna Pada Aplikasi NewSakpole Firdaus, Renaldi Irfan; Chamid, Ahmad Abdul; Jazuli, Ahmad
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 15, No 2 (2026): April 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i2.3478

To determine the success rate of a service, it is necessary to conduct sentiment analysis to understand public opinion and the level of public satisfaction, both positive, neutral, and negative. Sentiment analysis was used to improve the quality of service on the NewSakpole application in android-based vehicle tax payments. In this study, several stages were used such as data crawling, data preprocessing, word weighting using TF-IDF (Term Frequency Inverse Document Frequency) and SVM (Support Vectore Machine) classification model for sentiment classification. By using the Confusionsion Matrix test with a data sharing of 20% for data training and 80% for data testing, the accuracy results were obtained of 81.08%. The accuracy value of each sentiment also showed a fairly good performance, with a positive sentiment of 81.11%, a neutral sentiment of 78.62%, and a negative sentiment of 83.33%. These results show that the SVM algorithm is able to provide a fairly stable classification performance in this case study.Keywords: Sentimen Analysis; Google Play Store; NewSakpole; Support Vectore Machine AbstrakUntuk mengetahui tingkat keberhasilan suatu pelayanan, perlu dilakukan analisis sentimen untuk memahami opini publik dan tingkat kepuasan publik baik positif, netral, maupun negatif. Analisis sentimen digunakan untuk meningkatkan kualitas pelayanan pada aplikasi NewSakpole dalam pembayaran pajak kendaraan yang berbasis android. Dalam penelitian ini menggunakan beberapa tahap seperti crawling data, preprocessing data, pembobotan kata menggunakan TF-IDF (Term Frequency Inverse Document Frequency) serta model klasifikasi SVM (Support Vectore Machine) untuk klasifikasi sentimen. Dengan menggnakan pengujian Confussion Matrix dengan pembagian data 20% untuk data training dan 80% untuk data testing memperoleh hasil akurasi sebesar 81,08%. Nilai akurasi pada masing-masing sentimen juga menunjukkan performa yang cukup baik, dengan sentimen positif sebesar 81,11%, sentimen netral 78,62%, dan sentimen negatif 83,33%. Hasil ini menunjukkan bahwa algoritma SVM mampu memberikan performa klasifikasi yang cukup stabil pada studi kasus ini.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search