cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Bahrawi
Contact Email
bahrawi@kominfo.go.id
Phone
+62411-4660084
Journal Mail Official
jitu.journal@mail.kominfo.go.id
Editorial Address
Jl. Prof. Abdurrahmah Basalamah II No. 25 Makassar 90231
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
Journal of Information Technology and Its Utilization
Published by Sekolah Tinggi Multi Media Yogyakarta
ISSN : -     EISSN : 2654802X     DOI : 10.56873
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Mechanical Engineering
Journal of Information Technology and its Utilization adalah jurnal yang diterbitkan oleh Balai Besar Pengembangan Sumber Daya Manusia dan Penelitian (BBPSDMP Kominfo) Makassar. Bertujuan untuk menyebarluaskan hasil penelitian, kajian, rencangan ilmiah dibidang teknologi informasi dan pemanfaatannya. scope: data mining, Iot, Ai, digital processing, information system
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 77 Documents
 4   5   6   7   8 
COMBINING SUPERVISED AND UNSUPERVISED METHODS IN TOURISM VISITOR DATA Weksi Budiaji; Vebriana Vebriana; Juwarin Pancawati
Journal of Information Technology and Its Utilization Vol 5 No 1 (2022)
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.5.1.4659

Abstract

Combining supervised and unsupervised method can assist in the data analysis process. This research aims to apply a supervised method, i.e. Poisson regression, that is followed by an unsupervised method, namely cluster analysis of the visitors in a tourism dataset. The samples were taken 80 persons purposively from the visitors of the Flower Garden X in Serang Regency, Banten Province. The dataset consists of the number of visits, travel cost, income/ stipend per month, gender, age, distance from the place of origin, and perception, which is formed by 11 questions of facilities and services. The Poisson regression was applied in the 30, 40, and 50 bootstrap samples resulted in the perception as the significant features. Then, medoid-based cluster analysis, i.e. pam and simple k-medoids, in the perception dataset was applied. They compared simple matching and cooccurrence distances and were validated via medoid-based shadow value. It grouped the visitors into five clusters as the most suitable number of clusters. The combined methods of supervised and unsupervised provided the cleanliness as the important indicator. The improvement of the tourism object had to be focus on the cleanliness aspect.
NAIVE BAYES ALGORITHM IN HS CODE CLASSIFICATION FOR OPTIMIZING CUSTOMS REVENUE AND MITIGATION OF POTENTIAL RESTITUTION Hafizh Adam Muslim
Journal of Information Technology and Its Utilization Vol 5 No 1 (2022)
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.5.1.4740

Abstract

The Directorate General of Customs and Excise, as a government revenue collector, must maximise import duty receipts each year. One common issue is the return of unpaid import duty and/or administrative punishments in the form of fines based on the objection judgement document. The Tax Court could help you minimise your gross receipts at the Customs Office. Data mining techniques are intended to provide valuable information regarding the HS Code classification technique, which can assist customs agents in determining duties and/or customs values. This study makes use of data from the Notification of Import of Goods at Customs Regional Office XYZ from 2018 to 2020. The Cross-industry Standard Process for Data Mining (CRISP-DM) model is used in this study, and the Naive Bayes Algorithm in Rapidminer 9.10 is used for data classification. According to the model, the calculation accuracy is 99.97 percent, the classification error value is 0.03 percent, and the Kappa coefficient is 0.999..
NEXT WORD PREDICTION USING LSTM Afika Rianti; Suprih Widodo; Atikah Dhani Ayuningtyas; Fadlan Bima Hermawan
Journal of Information Technology and Its Utilization Vol 5 No 1 (2022)
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.5.1.4748

Abstract

Next word prediction which is also called as language modelling is one field of natural language processing that can help to predict the next word. It’s one of the uses of machine learning. Some researchers before had discussed it using different models such as Recurrent Neural Networks and Federated Text Models. Each researcher used their own models to make the prediction and so the researcher here. Researchers here chose to make the model using  Long Short Term Memory (LSTM) model with 200 epoch for the training. For the dataset, the researcher used web scraping. The dataset contains 180 Indonesian destinations from nine provinces. For the libraries, researchers used  tensorflow, keras, numpy, and matplotlib. To download the model in json format, the researcher used tensorflowjs. Then for the tool to code, the researcher used Google Colab. The last result is 8ms/step, loss: 55%, and accuracy: 75% which means it’s good enough and can be used to predict next words.
WEBSITE PHISING DETECTION APPLICATION USING SUPPORT VECTOR MACHINE (SVM) Diki Wahyudi; Muhammad Niswar; A. Ais Prayogi Alimuddin
Journal of Information Technology and Its Utilization Vol 5 No 1 (2022)
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.5.1.4836

Abstract

Phishing is an act to get someone's important information in the form of usernames, passwords, and other sensitive information by providing fake websites that are similar to the original. Phishing (fishing for important information) is a form of criminal act that intends to obtain confidential information from someone, such as usernames, passwords and credit cards, by impersonating a trusted person or business in an official electronic communication, such as electronic mail or instant messages. Along with the development of the use of electronic media, which is followed by the increase in cyber crime, such as this phishing attack. Therefore, to minimize phishing attacks, a system is needed that can detect these attacks. Machine Learning is one method that can be used to create a system that can detect phishing. The data used in this research is 11055 website data, which is divided into two classes, namely "legitimate" and "phishing". This data is then divided using 10-fold cross validation. While the algorithm used is the Support Vector Machine (SVM) algorithm which is compared with the decision tree and k-nearest neighbor algorithms by optimizing the parameters for each algorithm. From the test results in this study, the best system accuracy was 85.71% using SVM kernel polynomial with values of degree 9 and C 2.5.
Real-Time Smart System for Complaint Information System in Campus: Code of Conduct and Infrastructure Musawarman, Mr.; Fathi, Halimil; Setiawan, Ricak Agus
Journal of Information Technology and Its Utilization Vol 7 No 1 (2024): June 2024
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.7.1.5151

Abstract

In today's competitive business environment, maintaining high levels of customer satisfaction is crucial for the success of any organization. To effectively address customer complaints and concerns, businesses are increasingly relying on digital solutions such as complaint reporting systems. This paper presents the development of an online complaint reporting system designed to streamline the process of receiving, managing, and resolving customer complaints. The system incorporates features such as user-friendly interfaces, secure data storage, automated notifications, and real-time reporting functionalities. Through the implementation of this system, businesses can enhance their customer feedback management processes, improve customer satisfaction levels, and ultimately, strengthen customer relationships. Real-time reporting functionalities provide businesses with valuable insights into trending issues and customer pain points, allowing them to proactively address recurring problems and improve their products and services. By leveraging the online complaint reporting system, organizations can effectively capture, analyze, and respond to customer feedback in a timely manner, enhancing overall service quality and customer satisfaction. In conclusion, the development of an online complaint reporting system represents a significant step towards improving customer feedback management practices. By implementing this system, organizations can establish a more transparent and customer-centric approach to handling complaints, leading to enhanced customer loyalty and positive brand perception.
Model-View-Controller Design System of Motorcycle Damage Detection Using Forward Chaining Method Rismayani, Rismayani; Tahir, Muhammad Wahinuddin; Darwis, Muhammad; Nurani, Nurani; Pineng, Martina
Journal of Information Technology and Its Utilization Vol 6 No 2 (2023): December 2023
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.6.2.5230

Abstract

This study aims to design a motorbike damage detection system using the forward chaining method with a view controller model that can be run on a mobile-based system. Dealers and motorbike service providers receive and fulfil customer requests for motorbike service services. Mechanics who service vehicles still use conventional methods to check vehicle damage by scanning the paper (form). There is a list ofvehicle damage. This method takes quite a long time, and it is not sure that the problem will be resolved quickly. The research method used is forward chaining, and the model used is the Model View Controller, which separates data from the display by processing it. The result of this research is that with a motorbike damage detection system, mechanics from dealers and service areas do not have to carry out initial checks manually but instead use a system with a view controller model and initial check results. Detection can also be determined by applying the forward chaining method. Based on functional testing of the system using a black box, valid results were found; then, for logic testing using the forward chaining method, the results were free from logical errors.
Optimization of K Value in Clustering Using Silhouette Score (Case Study: Mall Customers Data) Mulyani, Heti; Setiawan, Ricak Agus; Fathi, Halimil
Journal of Information Technology and Its Utilization Vol 6 No 2 (2023): December 2023
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.6.2.5243

Abstract

Clustering is an important phase in data mining. The grouping method commonly used in data mining concepts is using K-Means. Choosing the best value of k in the k-means algorithm can be difficult. In this study the technique used to determine the value of k is the silhouette score. Then, to evaluate the k-means model uses the Davies Bouldin Index (DBI) technique. The best DBI value is close to 0. The parameters used are total consumer income and spending. Based on the results of this study it can be concluded that the silhouette score method can provide a k value with optimal results. For mall customer data of 200 data, the most optimal silhouette score is obtained at K = 5 with a DBI = 0.57.
Development of a Custom Technical Incident and Spare Part Management System for Effective Telecom Network Service Delivery Babalola, Falana Jimoh; Moruff, Oyelakin Akinyemi
Journal of Information Technology and Its Utilization Vol 7 No 1 (2024): June 2024
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.7.1.5246

Abstract

Managing technical incident in telecommunication industry is very important in order to ensure business continuity. However, there is a need to find effective ways of managing spare parts when there is a need for the replacement of such spare parts in order to fix technical incidents. That is why telecom operators require relevant systems for adequate incident and spare part management. With the outsourcing arrangement between some  operators and third-party site handlers in Nigeria and most developing countries, there is a need for proper technical incident handling and spare part management. Many of the problems that arise in telecommunication operation come from non-correlation of escalation with the spare part required to restore normal operation of the service after an interruption. This research focuses on designing and developing a web-based system for handling proper management of technical issues and provision of required spare parts promptly as required. This is to ease operations and communications among telecom operators and their technical service providers. The system was built using combination of web development tools such as Jinja Templating Engine, CSS, HTML, JavaScript, JQuery, Python, Flask and SQLite. The developed system has been tested and found useful for the scenarios that it was developed for. The solution allows online management of spares parts, tracking of escalations, provision of fault details and capturing of all faulty equipments due for repairs. It is believed that the custom system can help in achieving effective telecom network service delivery by the company that uses such approach.
Design of Rectangular Patch Microstrip Antenna with Defected Ground Structure Method at 3.5 GHz Frequency for 5G Technology Kartikasari, Galuh; Praja, Muhammad Panji Kusuma; Romadhona, Shinta
Journal of Information Technology and Its Utilization Vol 6 No 2 (2023): December 2023
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.6.2.5259

Abstract

5G technology is currently developing rapidly in various countries. 5G technology has three sub-frequencies: low band, midband and high band. Midband frequencies in Indonesia are between 2.6 GHz and 3.5 GHz. In order for 5G technology is able to be used in Indonesia, it needs an antenna that can work at 3.5 GHz and has a wide bandwidth. Microstrip antenna is a simple and efficient antenna. However, microstrip antenna has minimal bandwidth. To overcome this, certain methods are needed, one of which is the defected ground structure (DGS) method. The initial design of the antenna has dimensions according to the results of the calculation formula. Then optimization is carried out by reducing the dimensions of the antenna components. After that, the DGS method is applied to widen the bandwidth. The initial design of the single-patch antenna before using the DGS method has a return loss value of -19.96 dB, VSWR 1.22, with a gain value of 3.812 dB and bandwidth 105.1 MHz. The simulation results of the antenna using DGS have a return loss value of -39.76 dB, VSWR of 1.02, with a gain value 3.16 dB and a bandwidth of 158.4 MHz. These results prove that the use of the DGS method can increase bandwidth.
Expert System for Pest Diagnosis on Local Black Rice Plant in East Kalimantan Using the Naive Bayes Method Puspitasari, Novianti; Septirini, Anindita; Paripurna, Rian Bintang; Samsumar, Lalu Delsi
Journal of Information Technology and Its Utilization Vol 6 No 2 (2023): December 2023
Publisher : Sekolah Tinggi Multi Media "MMTC" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.6.2.5271

Abstract

Rice plant is a food crop that produces rice as the staple food for the majority of Indonesian people. Local rice which significantly contributes to fulfill the national rice consumption is black rice produced in East Kalimantan. However, local black rice often experiences crop failure due to pest attacks and environmental factors. The amount of local black rice production also continues to decrease due to limited human resources who have the skills and knowledge to diagnose pests in black rice plants. Therefore, one effort that can be made to overcome this problem is to create an expert system that can diagnose pests and diseases in black rice plants. The expert system in this research uses the Naive Bayes method, which identifies 11 types of pests that attack black rice plants and 34 symptoms caused by these pest attacks. Naive Bayes can provide information about the percentage of pests that rice plants might experience. Based on the results of the test cases, an accuracy value of80% was obtained, so the expert system built in this research can diagnose pests on black rice plants quite well.

Page 7 of 8 | Total Record : 77

 4   5   6   7   8 

Filter by Year

2018 2024


Reset
Filter By Issues
All Issue Vol 7 No 2 (2024): December 2024 Vol 7 No 1 (2024): June 2024 Vol 6 No 2 (2023): December 2023 Vol 6 No 1 (2023): June 2023 Vol 5 No 2 (2022): December 2022 Vol 5 No 1 (2022) Vol 5, No 1 (2022) Vol 4, No 2 (2021) Vol 4 No 2 (2021) Vol 4, No 1 (2021) Vol 3, No 2 (2020) Vol 3, No 1 (2020) Vol 2, No 2 (2019) Vol 2, No 1 (2019) Vol 1, No 2 (2018) Vol 1, No 1 (2018) More Issue