cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Syaifudin
Contact Email
jurnal_intelmatics@trisakti.ac.id
Phone
+628129513950
Journal Mail Official
jurnal_intelmatics@trisakti.ac.id
Editorial Address
Building E, floor 4, Department of Informatics Engineering, Universitas Trisakti
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
Intelmatics
Published by Universitas Trisakti
ISSN : -     EISSN : 27758850     DOI : https://doi.org/10.25105/itm
Core Subject : Science,
Computer Science & IT
The IntelMatics Journal is a scientific journal published by the department of informatics engineering at Trisakti University. The purpose and objective of the publication of the IntelMatics journal are as a means of dissemination of international standard science in the field of software engineering, information security, and business analysis in the scope of data intelligence and visualization. Journal will be published every sixth month
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 80 Documents
 4   5   6   7   8 
Brain Tumor Detection System Based on Convolutional Neural Network Febrianto, Nanang Dwi; Mardianto, Is; Rochman, Abdul; Najih, Muhammad
Intelmatics Vol. 5 No. 1 (2025): January-June
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i1.22135

Abstract

Early detection of brain tumours is essential to improve the effectiveness of treatment. This study develops a Convolutional Neural Network (CNN) model to detect brain tumours from MRI images. Using a dataset of 4410 images, the model was trained and tested with several CNN architectures, such as EfficientNetB0, InceptionNetV3, ResNet, MobileNet, VGG16, Model 1. Results showed that the best model achieved 97.8% accuracy, thus being able to predict brain tumours with a high degree of reliability. These findings support the application of CNNs in medical detection systems to assist doctors in faster and more accurate diagnosis.
Redesigning the UI/UX of a Mobile-Based Employee Presence Application at PT. Menara Indonesia Using the Design Thinking Method Putri, Nabilah; Syaifuddin; Pratiwi, Dian
Intelmatics Vol. 5 No. 1 (2025): January-June
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i1.22420

Abstract

A mobile-based presence application ensures accurate and efficient presence tracking. However, poor UI/UX can hinder productivity and user comfort. This study redesigns the UI/UX of PT. Menara Indonesia’s employee presence application using the Design Thinking method, which includes empathize, define, ideate, prototype, and test stages.The redesigned prototype was evaluated using the System Usability Scale (SUS), scoring 90 for administration and 80 for employees, indicating improved usability. The new design enhances comfort, efficiency, and ease of use, making the application more user-friendly. This study serves as a reference for future development in optimizing presence applications to better meet user needs.
The Opportunity of Ai Technology to Increase The Value Chain of Oil Palm Plantation Sediyono, Agung; Solihah, Binti
Intelmatics Vol. 5 No. 1 (2025): January-June
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i1.22477

Abstract

Indonesia produced 58,4% of worldwide oil palm production, and the contribution of the plantation sub-sector in 2022 is 3,76% of PDB and 30,32% of the Agriculture, Forestry, and Fishery sectors. However, oil palm production in Indonesia is lack of productivity and efficiency compared to other countries, especially Malaysia.  Therefore, this paper tries to explore the opportunities of AI technology to increase the value chain of the oil palm plantation, especially in productivity and efficiency. The scope of exploration started from oil palm seeding, nursery,  planting,  and harvesting. Based on the oil palm plantation value chain review and the previous research works in AI implementation on value chain respectively, it can be concluded that AI technology has been explored to be implemented in oil palm plantations intensively. However, there is still enough room for improvement especially in accuracy rate and adoption feasibility for smallholder planters. Moreover, IoT and drone technology have a big potential to be adopted because the plantation is mostly hard-to-reach areas by humans, for instance high oil palm bunch, long distance journey for inspection and maintenance, wild animal threat, etc.  
UI/UX Development for Tour Ticketing on Pari Island using User Centered Design Hudzafah, Abdullah; Pratiwi, Dian; Sari, Syandra
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.21023

Abstract

UI/UX Development of UCD-Based Tourism Tour Ticketing on Pari Island, which currently feels like the method of ordering tourism services on Pari Island is still too conventional, especially in the tourism sector. In fact, purchasing tourism tour tickets with methods that follow technological developments greatly influences efficiency in handling the surge of tourists coming to Pari Island, especially on weekends and other holidays. On Pari Island, purchasing tickets for tourism such as homestays, catering, snorkeling equipment rentals, bicycles, and motorbikes is still considered conventional where tourists who come to Pari Island must look for homestays and book tickets directly on the spot, in this study an application was created with a simple and attractive ticket purchasing concept (E-Ticket) which aims to improve the UCD-based tourism tour ticket ordering system on Pari Island.
Development of Osteoporosis Prediction System on Femur and Tibia Bones with Convolutional Neural Network Akhdan, Muhammad; Pratiwi, Dian; Rochman, Abdul
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.23237

Abstract

Osteoporosis and osteopenia are conditions that commonly affect bone health significantly, this is characterized by decreased bone density causing the risk of fractures especially in the femur and tibia. The prevalence rate of these diseases is calculated from 103,334,579 people between the ages of 15 and 105 years, with an overall prevalence of 18.3%. Fast and accurate detection is needed for the first line of defense for osteoporosis patients and potential patients. This study provides the development of a Convolutional Neural network (CNN) model trained to predict osteoporosis and osteopenia from x-ray radiographs of femur and tibia bones. The proposed model has satisfactory performance on all metrics namely average accuracy 90%, average recall 90%, average F1 score 90%. From these performance results, alternative detection methods using CNN can be considered by medical parties or parties who can utilize the first diagnosis of osteopenia to osteoporosis bone disease handling compared to conventional methods.
Analysis of the Suitability of Fortigate Firewall Performance Limiting the Use of Social Media Streaming During Operating Hours at PT. Asaba Digital Innotech Saputra, Erwan; Budi Santoso, Gatot; Sediyono, Agung
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.23394

Abstract

Initial network analysis at PT ASABA Digital Innotech identified very high bandwidth consumption for non-work activities, with total usage in 30 days reaching 195 GB for social media and 448 GB for streaming media. This research aims to implement and measure the effectiveness of access restriction policies using Fortigate firewalls to significantly reduce this traffic. Using the Network Development Life Cycle (NDLC) method, a rule policy based on FortiGuard Web Filtering and Application Control was designed to block access during working hours (08.00-17.00), with the exception of breaks (12.00-13.00) and for specific user groups (Board of Directors and Marketing team).The implementation results show a drastic and measurable decrease in bandwidth usage. Social media traffic was reduced from 195 GB to 7 GB, equivalent to a 96.41% reduction.Meanwhile, streaming media traffic dropped from 448 GB to 52 GB, a reduction of 88.39%.The effectiveness of the policy was validated through analysis of firewall logs that consistently displayed a Deny status: UTM Blocked for thousands of prohibited access attempts. Based on this data, it is concluded that the Fortigate configuration is very effective in optimizing network bandwidth usage. This study recommends the use of schedule policies for flexibility and the integration of deep packet inspection to anticipate bypass methods by users.
The Design of a Revenue Dashboard for the Operational Division of PT XYZ Using the Kimball Four-Step Method Arisandi, Debi; Siswanto, Teddy; Salim, Agus
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.23716

Abstract

The rapid development of information technology drives the need for effective and efficient decision-making systems, particularly in the business world. This study aims to design a dashboard integrated with the operational division system of PT XYZ to address issues of slow decision-making processes. The dashboard is designed using the Online Analytical Processing (OLAP) for Step Kimball method, enabling multidimensional data analysis.The design process includes several stages: identifying requirements, designing a data warehouse based on the Kimball method, processing data using OLAP, and visualizing data with Tableau. The data utilized comprises critical information from the operational division, such as company profiles, contracts, collections, revenue, and credit scores. The results demonstrate that the designed dashboard effectively provides relevant information to support fast and accurate decision-making needs. The implementation of this dashboard is expected to improve operational efficiency and provide better strategic insights for PT XYZ.
The Role of the Project Owner in Agile Project Management: A Case Study of the Kinerjapro Application Development at PT.Menara Indonesia Wibowo, Nurafni Revita; Syaifudin; Solihah, Binti
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.23821

Abstract

This study aims to design a web-based project management information system for monitoring internships at PT Menara Indonesia. The background of the study is the Merdeka Belajar Kampus Merdeka (MBKM) program, which enhances students' competencies in the workforce, as well as the challenges of manual internship monitoring, such as the risk of losing project records, limited storage, and inefficiency in communication and project coordination. The system is developed using the Agile Scrum method, following 5 sprints that include Product Backlog, Sprint Planning, Daily Scrum, Sprint Review, and Sprint Retrospective. The features developed include login, project and task management, messaging system, team member management, and basic report and event features. The Scrum implementation improves operational efficiency and data transparency. The result is a web-based project management information system that overcomes manual monitoring issues, increases efficiency, and facilitates better coordination among teams at PT Menara Indonesia, providing faster and more transparent information access.
Analysis of CNN for Detecting Footsteps in Physical Traces App Nadin, Annisa; Zuhdi, Ahmad; Shofiati, Ratna
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.23892

Abstract

Step detection is an essential feature in promoting healthy living through mobile applications. This study evaluates the accuracy of a Convolutional Neural Network (CNN) model implemented in the Physical Traces application for detecting steps based on accelerometer and gyroscope sensor data. Data were collected through experimental activities where 60 participants walked 20 steps and ran 10 meters, repeated three times each. The results show average accuracy exceeding 100%, indicating a tendency for overcounting. Evaluation was performed using Absolute Error, Relative Error, Symmetric Accuracy, and SMAPE. Statistical analysis (Mann-Whitney, Kruskal-Wallis), reliability test (Cronbach’s Alpha = 0.9178), and validity test (positive correlations) revealed significant differences by gender and age group. These findings indicate that CNN-based step detection works effectively, but improvements are necessary to address individual variability and real-world conditions.
Optimizing Agricultural Land Fertility through Nutrient Content and pH Analysis Tamam, Moh. Badri; Anwari; Rofiuddin; Supriatin
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.24051

Abstract

This research addresses the challenge of declining soil fertility in Pamekasan, East Java, by proposing a machine learning approach to improve the accuracy of soil fertility classification and provide data-driven recommendations. Conventional methods like linear regression and expert systems are limited in capturing the complexity of soil variables, leading to less accurate results. Therefore, this study compares the performance of two machine learning algorithms, Random Forest and XGBoost, in classifying soil fertility levels based on nutrient content (N, P, K, and micronutrients) and soil pH. The dataset, consisting of 880 soil samples from Pamekasan, revealed an imbalance, with the high-fertility class accounting for only 39 samples. After data preprocessing, both models were evaluated. The Random Forest model achieved an overall accuracy of 90.34%, slightly outperforming XGBoost, which reached 88.64%. Random Forest demonstrated superior performance in detecting low-fertility land (recall 0.97) and medium-fertility land (precision 0.93, recall 0.88). For the high-fertility minority class, Random Forest showed better recall (0.60) than XGBoost (0.40), while maintaining perfect precision (1.00). The study concludes that Random Forest is the optimal model for classifying soil fertility in Pamekasan. These findings provide a basis for more precise, efficient, and sustainable fertilization recommendations, which are expected to help farmers optimize productivity and support the sustainability of the local agricultural ecosystem by reducing excessive fertilizer use.

Page 7 of 8 | Total Record : 80

 4   5   6   7   8 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): January-June (In Progress) Vol. 5 No. 2 (2025): July-December Vol. 5 No. 1 (2025): January-June Vol. 4 No. 2 (2024): Juli-Desember Vol. 4 No. 1 (2024): Januari-Juni Vol. 3 No. 2 (2023): Juli-Desember Vol. 3 No. 1 (2023): Januari-Juni Vol. 2 No. 2 (2022): Juli-Desember Vol. 2 No. 1 (2022): Januari-Juni Vol. 1 No. 2 (2021): Juli - Desember Vol. 1 No. 1 (2021): January More Issue