Claim Missing Document
Check
Articles

Digitalisasi Layanan Pengaduan Pelanggan melalui Sistem Informasi Berbasis Web pada PERUMDA Air Minum Tirta Jaya Mandiri Kabupaten Sukabumi Bilqis Zahra; Kamdan Kamdan; Ivana Lucia Kharisma
Jurnal Pengabdian Masyarakat Bhinneka Vol. 4 No. 4 (2026): Juli
Publisher : Bhinneka Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58266/jpmb.v4i4.1587

Abstract

Perumda Air Minum Tirta Jaya Mandiri Kabupaten Sukabumi menghadapi persoalan pengelolaan pengaduan pelanggan yang masih dilakukan manual dan tersebar di 21 cabang tanpa basis data terpusat, sehingga manajemen pusat tidak memiliki visibilitas real-time dan pelanggan tidak memiliki kanal digital untuk menyampaikan keluhan. Kegiatan pengabdian ini bertujuan membangun portal pengaduan publik berbasis web dan dashboard administrasi terintegrasi dengan kontrol akses berbasis peran, dilengkapi modul klasterisasi otomatis dan modul peramalan tagihan bulanan berbasis machine learning. Metode yang digunakan meliputi empat tahap, yaitu analisis kebutuhan, perancangan sistem, pengembangan modul berupa portal berbasis Flask, dashboard berbasis Streamlit, dan modul analitik lanjutan, serta tahap integrasi, pengujian, dan deployment sistem. Kegiatan ini menghasilkan dua sistem yang terintegrasi melalui satu basis data bersama sehingga pengaduan pelanggan tersinkronisasi secara real-time tanpa entri ulang data, klasifikasi pengaduan menjadi konsisten antarcabang, serta modul peramalan tagihan menunjukkan bahwa algoritma XGBoost memberikan performa prediksi terbaik dibandingkan tiga algoritma pembanding lainnya. Integrasi ini terbukti mempercepat alur informasi, meningkatkan transparansi penanganan pengaduan, dan memberikan manajemen pusat visibilitas agregat atas kinerja seluruh cabang. 
Pengembangan Sistem Klasifikasi Citra Daging Sapi Dan Daging Babi Berbasis Web Menggunakan DENSENET-121 Siti Nurviatika; Ivana Lucia Kharisma; Nugraha
Jurnal Sains Informatika Terapan Vol. 5 No. 2 (2026): Jurnal Sains Informatika Terapan (Juni, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i2.1176

Abstract

The circulation of beef and pork products that are difficult to distinguish visually can create challenges for consumers, making an automated meat identification system necessary. This study aims to develop an image classification model for beef and pork using the Convolutional Neural Network (CNN) method with the DenseNet-121 architecture and to implement it in a Streamlit-based web application. The dataset used in this study consists of 6,000 images, comprising 3,000 beef images and 3,000 pork images collected from two different dataset sources. The dataset underwent several preprocessing stages, including resizing, contrast enhancement, normalization, and data augmentation, and was subsequently divided into training, validation, and testing sets with a ratio of 70:15:15. The results show that the DenseNet-121 model is capable of classifying beef and pork images with excellent performance. Based on the evaluation using a confusion matrix and classification report, the model achieved an accuracy of 97.89%, with high precision, recall, and F1-score values for both classes. The trained model was then deployed in a web application that allows users to perform classification through image uploads or direct image capture using a camera. Based on these findings, it can be concluded that the DenseNet-121 architecture is capable of classifying beef and pork images with high accuracy and has the potential to be utilized as a practical tool for meat type identification.
Website-Based Ergonomic Sitting Posture Detection Using YOLOV8 Pose Estimation Nurazizah Zahra; Ivana Lucia Kharisma; Somantri
Jurnal Sains Informatika Terapan Vol. 5 No. 2 (2026): Jurnal Sains Informatika Terapan (Juni, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i2.1177

Abstract

This study aims to develop a web-based ergonomic sitting posture detection system to reduce postural fatigue caused by prolonged computer use. The proposed system uses a deep learning-based pose estimation method to detect body keypoints and calculate the user's posture angles. The dataset used consists of hundreds of images that have been enhanced in quality and quantity through a data augmentation process. The system then classifies sitting postures into ergonomic and non-ergonomic categories. Test results show that the system is able to achieve a high level of accuracy, with the model achieving 98% Precision, 99% Recall, 99% mAP50, and 82% mAP50-95 in detecting and classifying sitting postures. Furthermore, the web-based implementation allows for real-time monitoring. The results of this study indicate that computer vision technology has the potential to be an effective solution to increase awareness of correct sitting posture and help prevent postural fatigue, especially in academic environments.
Implementasi Metode Fuzzy Logic Mamdani Untuk Rekomendasi Takaran Kombinasi Buah Penderita Diabetes Kania Purnarahayu; Indra Yustiana; Ivana Lucia Kharisma
Jurnal Sains Informatika Terapan Vol. 5 No. 2 (2026): Jurnal Sains Informatika Terapan (Juni, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i2.1203

Abstract

Diabetes mellitus is a chronic metabolic condition that requires proper dietary management to keep blood glucose levels stable. Fruit is recommended for people with diabetes as it contains important nutrients; however, differences in carbohydrate and fibre content mean that careful consideration must be given to the choice of fruit combinations and portion sizes. This study aims to apply the Mamdani fuzzy logic inference method to generate recommendations for fruit combination portions based on carbohydrate and fibre content. Secondary data were obtained from the Indonesian Food Composition Table (TKPI), which comprises 10 types of fruit. Data processing involved fuzzification, the formulation of a rule base, Mamdani inference using the Min-Max operator, and defuzzification using the centroid method. The defuzzification results yield a compatibility value which is used to determine the recommendation category and the appropriate fruit combination portion. This method has been implemented in a web-based application to provide automatic recommendations to users. The research findings indicate that the Mamdani fuzzy logic inference method can effectively process carbohydrate and fibre content into measurable and easily understandable recommendations regarding fruit combination portions. The proposed system can assist people with diabetes in selecting suitable fruit combinations and appropriate portion sizes, thereby supporting healthier dietary planning and facilitating daily decision-making regarding fruit consumption.
Co-Authors adang badru jaman,anggun fergina, adang badru jaman,anggun fergina Ade Arian Adhitia Erfina Adisti Ridha Ramadhan Ai Solihah Algifari, M. Alwan Alida Fany Tariza Putri Alun Sujjada Alun Sujjada Alyanissa Putri Iskandar Andi Agusti Andi Nopiandi Andi Nopiandi Armelia Isabela Taek Asep Rizki Firdaus Asep Rizki Firdaus Atikah Mugiyanti Azkal Khalif Bilqis Zahra Dede Serlina Dendi Nasrulloh Dendi Nasrulloh Dewi Puspitasari Dhea Ayu Septiani Dhea Ayu Septiani Dila Aura Futri Dwi Sartika Simatupang E. Tesly Navida Elsy Rahajeng Fakhriyal Riyandi Yasin falentino sembiring Falya Amrina Zahra Fransiskus Octavianus Mado Hurint Galih Rakasiwi Galuh Ratna Putri Gina Purnama Insany Gina Purnama Insany Gina Purnama Insany Hermanto Ika Imam Sanjaya Indra Yustiana Indra Yustiana Ira Rohimah Junjun Junaedi Kamdan Kamdan Kamdan Kania Purnarahayu Lufita Alvira Maximillian Huang Mayang Selpiyana Mega Putri Utami Meutia Riany Meylinda Nuryani Mirna Kamilah Moh. Abd. Aziz Hidayat Muhamad Galih Sundayana Muhamad Rizky Fauzi Muhammad Dafik Kholik Firdaus Muhammad Ikhsan Thohir Muhammad Ikhsan Thohir Muhammad Raihan Asshafwat Muslih, Muhamad Naufal Nuryanto Neng Syahla Nida Khofifah Nieka Julyana Nugraha Nur Hidayah K Fadhilah Nurani Istiaen Nurazizah Zahra Paikun Pascal Aditia Muclis Purnama Insany, Gina Putri Anugrah S Putri Iskandar, Alyanissa Resma Nuraeni Rismi Nurlaely Rizki Haddi Prayoga ROSNIA YURISTA Saila Julia Sally Agustin Elisya Salman Alhidamkara Sany Noor Fauzianty Setiana Andika Putra Setiawati Siti Nurviatika Siti Sarah Sobariah Lestari Somantri Somantri Somantri Somantri Suhendar Suhendar Teguh Gumelar Teguh Gumelar Tofik Hidayat Tri Hadianto Widy Karisma Wigi Januar Rahman Wilda Widyana Yusup Solehudin Zilfa Agustina Munawar