cover
Contact Name
Dewa Made Sri Arsa
Contact Email
dewamsa@unud.ac.id
Phone
-
Journal Mail Official
jurnal.merpati@unud.ac.id
Editorial Address
Gedung Teknologi Informasi-Fakultas Teknik Jalan Raya Kampus UNUD, Jimbaran, Badung, Bali
Location
Kota denpasar,
Bali
INDONESIA
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi)
Published by Universitas Udayana
ISSN : 22523006     EISSN : 26852411     DOI : https://doi.org/10.24843/JIM
Core Subject : Science,
The journal publishes work from all disciplinary, theoretical and methodological perspectives. It is designed to be read by researchers, scholars, teachers and advanced students in the fields of Information Systems and Information Science, as well as IT developers, consultants, software vendors, and senior IT executives seeking an update on current experience and future prospects in relation to contemporary information and communications technology.
Articles 280 Documents
Design and Development of Web-Based E-CRM (Electronic Customer Relationship Management) at Bali Tangi Zoltan, Daniel Syah Reza; Susila, Anak Agung Ngurah Hary; Githa, Dwi Putra
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p03

Abstract

Bali Tangi is a company engaged in body care and beauty. Bali Tangi strives to enhance customer satisfaction in selling skincare and beauty products in the face of increasing business competition. The aim of this research is to design and develop a web-based E-CRM application to help the company strengthen customer relationships and improve customer satisfaction. The research method used consists of stages of problem and needs identification, literature study, analysis of CRM phases and business processes, system design and development according to needs, system testing, and system implementation through hosting. The results of functionality testing using black box testing indicate that the system can be used according to its functions. The final score of usability testing, measuring usability by users, is calculated from the total average of all indicators and shows a score of 4.13 with a satisfactory category for users.
Maidekost Website Improvement Recommendations Based on User Experience and USE Questionnaire Evaluation Maricar, M. Azman; Edwar, Edwar; Simangunsong, Batara FS; Anisa, Aura Pirdaraya Nur
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p02

Abstract

The troublesome search for temporary housing information is the background for the creation of the Maidekost platform. The Maidekost website has existed since its inception but has not been operational until now. This raises the assumption that there is a problem with usability. Maidekost has been evaluated from a usability perspective with interviews and the USE Questionnaire. The results of a high usability predicate and a feasibility percentage of 79.96% were obtained and several things needed to be fixed. The focus of this study aims to provide recommendations for improvement in the form of a prototype and these recommendations are tested again with the USE Questionnaire. The results obtained are an increase in the average usability of 0.11 but does not affect the usability predicate, which is still at the high predicate. In terms of the percentage of eligibility, there was an increase of 1.95%, so that it became 81.91% which was initially feasible to be very feasible to use. In other words, the recommendations given are able to increase usability and can be implemented.
Evaluation and Improvement of User Interface Design in Mobile Delivery Services With User Centered Design Approach and Heuristic Evaluation (Case Study: Kirimaja Application) Ardhani, Ni Komang Sucitra; Wirdiani, Ni Kadek Ayu; Rusjayanthi, Ni Kadek Dwi
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p07

Abstract

KirimAja is a mobile-based goods delivery service application that is useful for helping people to send goods easily. This application has several features for sending goods, such as the Sameday Service, Nextday Service, Regular Service, Check Rates, and Check Receipts features. Usability problems in the KirimAja application were found based on observations and responses found in the "Google Play Store" and "App Store", namely in an unattractive appearance and display of error messages that were not well understood, therefore a usability evaluation and improvement of the user interface design are needed help the user when using the application. Evaluation and improvement of the user interface design in the KirimAja application uses the User Centered Design approach and the Heuristic Evaluation method, while testing user satisfaction with the KirimAja application uses the System Usability Scale method. The design improvements made resulted in increased results, namely by using the Heuristic Evaluation method to get scores on the H5 Error Prevention and H9 Help Users Recognize, Diagnoze, and Recover from Errors aspects from 2 to 0, while using the System Usability Scale method experienced an increase in the grade scale from D to A.
Enterprise Resource Planning (ERP) Business Process Reengineering with Accelerated SAP (ASAP) and Kanban Methods (Case Study: Sahana Bali Craft) Liukae, Herry Daniel Prasetia; Pratama, I Putu Agus Eka; Putri, Gusti Agung Ayu
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p04

Abstract

Sahana Bali Craft, a handicraft company that produces Ayaman Bags typical of Tengenan Village, Karangasem Regency, Bali where through the results of interviews and observations, it was revealed that this company faced obstacles in recording production and cost calculations that were still done manually, application of the Make to Order concept was not well integrated, and the company did not have an Enterprise Resource Planning system and re-engineering was carried out. This research recommends the implementation of business process re-engineering as an effort to improve business process efficiency with the ASAP and Kanban methods. The ASAP method is used in designing ERP systems to optimize costs, time, and available resources, while the Kanban method is applied in project management at the business blueprint and realization stages. The business process engineering has been tested with the User Acceptance Testing method and shows 1320 < 1718 < 1760 which means that the proposed business process system is considered positive or quite successful for the company.
Medical Costs Estimation Using Linear Regression Method Dwikasari, Ni Made Dita; Sutramiani, Ni Putu; Putri, Komang Sri Yanisa; Kusuma, Nyoman Tri Rahaditya; Pramana, Made Dimas Aldi Dwi; Darma, I Wayan Agus Surya
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p03

Abstract

Medical costs are a significant issue in the health sector. High healthcare cost lead to the need to anticipate financial risks for individuals and insurance providers. Therefore, medical cost data analysis is necessary to estimate future medical expenses. This research implements data mining techniques using Simple and Multiple Linear Regression methods to estimate medical costs. The dataset used consists of insurance claim data obtained from Kaggle, which includes attributes such as age, gender, body mass index, number of children, smoking habits, region, and medical charges. The research findings that Multiple Linear Regression outperforms Simple Linear Regression in estimating the provided dataset, with R2 value of 80% and lower ?? MSE and MAE values than Simple Linear Regression. The application of linear regression in insurance claim data analysis can provide significant benefits for patients, hospitals, and insurance providers. Overall, this research highlights the effectiveness of data mining techniques, specifically linear regression, in estimating healthcare costs.
Development of Balinese Cosmetology Marketplace Application on Android Based Wirdiani, Ayu; Sudana, Oka
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p08

Abstract

Appearance is the main thing for women. An attractive appearance makes a person more confident. This shows that the demand for personal beautification services is still high, and is a promising beauty business opportunity. Apart from daily grooming, salon and cosmetology businesses are also in high demand at certain events such as graduations, weddings and dance events. In the pandemic era, most people are reluctant to leave the house to get treatment, they want something practical that can be ordered online. Based on this, a solution was created in the form of an online application so that people can order make-up and body care at home. In this application there will be three users, namely salon admin, customer and therapist staff. The test results using the black box method which were tested by 15 salon customers produced a percentage of 87.96%, which means the application is very suitable for development. The test results with usability testing show that the satisfaction indicator is the highest indicator.
Architectural Design of an Electronic Based Government System (Case Study of XYZ district government) Yanti, Lidya; Wirdiani, Ni Kadek Ayu; Githa, Dwi Putra
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p05

Abstract

The design of the Electronic-Based Government System Architecture to develop basic framework related to integration between SPBE Architecture domains, such as Business Processes, Services, Applications, Data and Information, Infrastructure, and Security. The results showed the SPBE mapping produces 17 business processes, 44 services, 112 applications, 123 data and information. SPBE infrastructure mapping has several divisions, such as computing facilities, platforms, and system integration. SPBE security mapping has several parts, such as technical standards and security procedures, SPBE security implementation, and SPBE security feasibility. The SWOT analysis concludes the strengths are business processes, services, and SPBE applications are sufficient to support the performance of government administration services and public services. The incomplete data used to complete the infrastructure and security domains of SPBE is a weakness, opportunity, and threat. The opportunity is can provide a clear direction in the implementation of SPBE has the opportunity to increase the SPBE index value. Keywords: Architectural Design, Government System Based Electronic, SPBE, SWOT Analysis.
Ships Detection on Aerial Imagery using Transfer Learning and Selective Search Dewi, Desak Ayu Sista; Sri Arsa, Dewa Made; Susila, Anak Agung Ngurah Hary; Widyantara, I Made Oka
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 3 (2023): Vol. 11, No. 3, December 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i03.p04

Abstract

The traffic in the water area such as harbor and sea strait is highly important to be monitored because it helps to minimize unwanted ships accident. As a result, we proposed an automatic detection method to localize ships contained in sattelite image. We examine several deep learning method as the classification backbone, namely MobileNetV2, DenseNet121, VGG16, and ResNet50. Afterwards, we employed the trained model for detecting the ships. To make the detection faster, inspite of using a sliding window, we use selective search to sample the object candidates from the given scene. The experiments was done using Shipsnet dataset and tested on aerial images. We also conducted a cross domain evaluation where the images were taken using Google Earth. The results indicate that MobileNetV2 has the best performance on classification and detection tasks. The MobileNetV2 is also able to detect the ships on cross-domain scenarios.
Classification of Meat Freshness using Deep Learning Wirdiani, Ayu; Oka Sudana, Agung
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p01

Abstract

Meat is a source of food protein that is quite popular among people. The price of meat tends to be expensive, causing many meat sellers to mix fresh meat with less fresh meat. Meat that is not fresh enough can affect the health of people who consume it. Based on these problems, research was created that can differentiate the freshness of meat using digital images. In this research, the meat that will be used as research objects is beef and chicken. The freshness of meat will be differentiated based on color and texture using deep learning. The processes carried out are the preprocessing process, data augmentation, feature extraction is carried out using color features and texture features using the Gray Level Cooccurrence Matrix (GLCM) method, training process and classification process using deep learning. The training process is carried out using the CNN method, such as ResNet 18, ResNet 34 and ResNet 50 architectures. The test results using three types of ResNet architecture obtained the best results using ResNet18, epoch 10 with an accuracy of 94%.
FastText and Bi-LSTM for Sentiment Analysis of Tinder Application Reviews Dyanggi, Anak Agung Mayra Candra; Darma, I Wayan Agus Surya; Sastaparamitha, Ni Nyoman Ayu J.
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 1 (2024): Vol. 12, No. 1, April 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i01.p07

Abstract

Nowadays technology affects all aspects of society, one of the innovations and creativity in the field of technology is the emergence of online dating application media. The application makes it easy for users to find a partner according to their respective criteria. The most popular online dating app is Tinder. The rise of the use of online dating applications invites controversial sentiments in the community. With this problem, a sentiment analysis is needed to find out the opinions and views of users about Tinder. This study proposed the fastText and Bi-LSTM models used to determine the optimization performance of the fastText and Bi-LSTM methods in sentiment analysis and compares the performance of the fastText and Bi-LSTM models with the fastText and Bidirectional Encoder Representations from Transformers (BERT) models. Based on the experiment, fastText and Bi-LSTM produced the highest performance in the 4th fold scenario with 88% accuracy. Based on the comparison of the three model performances, the fastText and BI-LSTM models can outperform the fastText and BERT models on sentiment analysis of user review datasets in the Tinder application.