Claim Missing Document
Check
Articles

Found 17 Documents
Search

Perancangan Desain User Interface Pada Sistem Registrasi Pasien Di Rumah Sakit Graha Husada Putri, Siti Yuliana; santi, nirma ceisa; Rokhim, Auliyaur
Multidisciplinary Applications of Quantum Information Science (Al-Mantiq) Vol. 5 No. 1 (2025): Multidisciplinary Applications of Quantum Information Science (Al-Mantiq)
Publisher : Al-Mantiq

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32665/almantiq.v5i1.5526

Abstract

Technology is currently a tool for society, especially in public services, one of these public services is in the health sector. In the health sector, several health services such as clinics, hospitals and other health facilities have implemented technology to support their operational activities. Currently, many hospitals use computer-based systems to identify patients. One of them is a registration information system that makes services more efficient and effective. This research aims to design a user interface for a website-based patient registration system using the Design Thinking method. The result of this research is a prototype design. The second stage above is applied to the prototype stage which is used as an example of the Ul display for the hospital patient registration application that will be developed. Based on Usability Testing using Google from and distributing online questionnaires. Of the 11 respondents testing the admin and user sections, the results from the respondents were 90%, These results indicate that almost all users are satisfied with the prototype design and the results of these respondents state that the patient registration website prototype is easy to use.
Analisis Sentimen Ulasan Aplikasi DANA di Google Play Store: Penerapan Support Vector Machine dan Synthetic Minority Over-sampling Technique Fajar Nawulansih, Dewi; Ceisa Santi, Nirma; Aristia Sa’ida, Ita
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 9 (2025): JPTI - September 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.1053

Abstract

Analisis sentimen ulasan pengguna aplikasi DANA di Google Play Store menggunakan algoritma Support Vector Machine (SVM). Ketidakseimbangan data ditangani dengan Synthetic Minority Over-sampling Technique (SMOTE), dan optimasi parameter dilakukan melalui GridSearchCV. Sebanyak 1.000 ulasan terbaru dianalisis setelah pre-processing dan transformasi TF-IDF. Model SVM dengan kernel linear menghasilkan akurasi tertinggi sebesar 90%, meningkat dari 84% sebelum penerapan SMOTE dan tuning. Uji paired t-test terhadap hasil 10-fold cross-validation menunjukkan peningkatan yang signifikan secara statistik (p-value < 0,05). Recall kelas negatif meningkat dari 63% menjadi 82%, sementara recall positif mencapai 94%. Word cloud menunjukkan kata “dana” paling sering muncul pada ulasan positif dan “aplikasi” pada ulasan negatif. Kombinasi metode ini meningkatkan performa klasifikasi sentimen terhadap ulasan aplikasi DANA secara signifikan.
Penerapan Metode Naïve Bayes pada Sistem Seleksi Penerima Bantuan Bedah Rumah Prastianti, Erlinda Nofa; Santi, Nirma Ceisa
Multidisciplinary Applications of Quantum Information Science (Al-Mantiq) Vol. 3 No. 2 (2023): Multidisciplinary Applications of Quantum Information Science (Al-Mantiq)
Publisher : Al-Mantiq

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32665/almantiq.v2i2.2005

Abstract

Home renovation is a succor given by the government for poor people to relieve their economics burden. Of CV Garuda Metta Consultant have team work there are with Dinas Cipta Karya and Dinas Bina Marga In Tambakrejo, Bojonegoro City, there is succor that coming from the region and the institution itself. The succor can be obtained if the candidates are suitable with the requirements and the criteria, such as land floor, bamboo wall, and unsafe roof condition. In addition, the criteria also specified on family income, land area of the house, and number of families. To select the candidates who get a chance of house renovation. This study will make a decision support system to help the get of home renovation receivers by the government in Sambirejo that using Naïve Bayes method. The purpose of this research is to provide suggestion for the priority of receivers of home renovation and to help the selectors in order that the receivers of home renovation in the Tambakrejo, Bojonegoro City in line with the target. This result of this research is a decision support system for the determination of the home renovation recipients based on defined criteria.
Peramalan Penjualan Semen Menggunakan Metode Single Moving Average dan Double Moving Average Yuliana, Nur Lutfi; Santi, Nirma Ceisa; Mahmudah, Nur
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8537

Abstract

UD. Kurnia Makmur is a shop that sells various building materials including cement. Previously, the shop UD. Kurnia Makmur still had difficulty in determining the amount of cement stock that should be provided, UD. Kurnia Makmur often also experiences shortages or excess stock due to the rise and fall of inconsistent market demand. Therefore, a forecasting method is needed that can help make better decisions in estimating the amount of cement stock that must be provided. The method used to predict cement stock in this study is the single moving average and double moving average methods. The purpose of this forecasting study is for the company to know the amount that must be provided according to consumer demand for cement sales and to know the accuracy between the single moving average and double moving average methods. Because the previous journal showed that both methods produced a MAPE of less than 10% where, it can be interpreted that if the MAPE is less than 10% then the forecast is very good. In calculating the accuracy of this study using MAD (Mean Absolute Percentage Error) and MAPE (Mean Absolute Percentage Error) using Microsoft Excel as the calculation tool. After being calculated using Microsoft Excel, the results obtained in the study were MAD of 30.72 and MAPE of 2.0% for the single moving average, while the double moving average produced MAD of 19.0 and MAPE of 1.24%.
A Aplikasi Bulu Digital Inovasi E-government untuk Peningkatan Aksebilitas dan Kecepatan Pelayanan Pembuatan Surat Desa Yogi Noviana, Ovie; Mauliditya Valencia Yolanda, Regina; M. Nazyd Mavaza; Ceisa Santi, Nirma
Management of Information System Journal Vol 4 No 1: November 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/mis.v4i1.2342

Abstract

The development of the Bulu Digital application represents an innovation to support the e-Government Smart Village concept in Bulu Village, Bojonegoro Regency, East Java. This application is designed to facilitate digital administrative processes, enhancing efficiency, transparency, and accessibility of public services for residents. The approach employed includes participatory methods, Agile, and SDLC, involving community members and village officials through observation, interviews, and group discussions. The application enables residents to submit applications online, monitor their status, and manage digital archives that are secure and well-organized. In addition to accelerating service delivery and reducing the risk of document loss, this digital implementation also promotes technological literacy among villagers, thus accelerating the transition toward a self-reliant and modern village. This innovation is expected to serve as a model for other villages in utilizing technology to improve.
Implementasi Peramalan Stok Parfum Pada Imshop Parfum dengan Metode Weighted Moving Average Zulfiana Nur’aini; Nirma Ceisa Santi; Nur Mahmudah; Mula Agung Barata
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 10, No 2 (2025): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v10i2.894

Abstract

Humans are social creatures who need to communicate with each other. In this regard, it is necessary to provide comfort in a conversation. To provide this comfort, you can use perfume. Imshop Parfum is a shop that sells various choices of perfume scents, but of the various types of perfumes sold, of course there are perfumes that are the most popular and rarely purchased, this is certainly a problem if the stock of the item runs out or provides too much stock. The purpose of this study is to predict the stock of goods at Imshop Parfum. The method used in this study is the Weighted Moving Average with periods 3 and 5. The forecast results from the perfume study in June 2025 were 215 for period 3, and 212.86 for period 5. MAPE is 1.98% for period 3, and the MAPE value is 2.74% for period 5. It can be concluded that period 3 is the best and most accurate result because it has the smallest MAPE value.
Brain Tumor Classification in MRI Images Using Convolutional Neural Networks with Explainable Artificial Intelligence Muhammad Abdul Ghofur; Nirma Ceisa Santi; Hastie Audytra
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13594

Abstract

Brain tumors are a condition requiring rapid and accurate diagnosis. This study aims to enhance the transparency of Convolutional Neural Network (CNN)-based brain tumor classification models by implementing Explainable Artificial Intelligence (XAI) techniques, specifically Eigen-CAM and LIME. The models were developed using a transfer learning approach on ResNet50 and EfficientNetB0 architectures, utilizing a dataset of 3,000 MRI images categorized into glioma, meningioma, and pituitary tumor classes. Test results indicate that ResNet50 achieved the best performance, with accuracy, precision, recall, and F1-score values of 94%, while EfficientNetB0 achieved 93%. The application of 5-fold cross-validation improved the models' generalization capabilities and reduced the risk of overfitting. Visualizations using Eigen-CAM and LIME demonstrate that the models focus on relevant tumor regions, thereby increasing the transparency and reliability of MRI-based classification.