cover
Contact Name
Ari Zulsafar
Contact Email
zulsapar@telkomuniversity.ac.id
Phone
+6285280983983
Journal Mail Official
journals@telkomuniversity.ac.id
Editorial Address
Jl. Telekomunikasi No.1, Sukapura, Kec. Dayeuhkolot, Kabupaten Bandung, Jawa Barat
Location
Kota bandung,
Jawa barat
INDONESIA
IJoICT (International Journal on Information and Communication Technology)
Published by Universitas Telkom
ISSN : -     EISSN : 23565462     DOI : https://doi.org/10.21108/ijoict
Core Subject : Science, Social,
nternational Journal of Information Communication Technology (IJoICT) is a peer-reviewed Journal. This journal includes novel ideas on ICT, state of the art technique implementations, and study cases on developing countries. This journal fully acknowledges the articles that emphasize a balanced coverage between theory and practice. Subject areas that is suitable for publication to the following fields: Computer Networking and Communication Graphics & Multimedia Theoretical CS & Statistic Embeded System Software Engineering Information System Security & Cryptography Data Science Parallel and Distributed Systems Database Systems Intelligence System
Articles 17 Documents
Pose-Based Action Recognition in Tennis using MediaPipe and LSTM Walid Hanif Ataullah; Isa Mulia Insan; Sheina Fathur Rahman
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.9622

Abstract

Pose recognition in tennis is an essential aspect for analyzing playing techniques and evaluating athlete performance. This study develops a tennis pose recognition system that integrates MediaPipe for pose feature extraction with Long Short-Term Memory (LSTM) networks for movement classification. The research dataset consists of 2,010 images of tennis movements across four categories: backhand, forehand, ready position, and serve, annotated in COCO format. MediaPipe successfully extracted pose landmarks from 1,782 images (88.7%), generating 33 pose landmarks flattened into a 99-dimensional feature vector. The LSTM model is designed with a 3-layer LSTM architecture and 2 dense layers, trained using a stratified train-test split with an 80:20 ratio. Model evaluation uses various metrics including accuracy, precision, recall, and F1-score. The results show that the system achieves 90.20% accuracy, with the best performance in the ready position category (F1-score: 91.28%) and the lowest in the forehand category (F1-score: 88.89%). The model demonstrates good computational efficiency with a memory footprint of 714.39 KB, enabling deployment on mobile devices. This study contributes to the development of automated sports analysis systems and demonstrates the feasibility of integrating MediaPipe-LSTM for real-time tennis pose recognition applications.
Evaluating the Performance of Graph-Based Recommendation Systems: A Case Study on Amazon Data Zaid Mundher; Manar Talat Ahmad
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.9878

Abstract

Today, recommendation systems are considered a main component of social media platforms and many other online websites. Recommendation systems can be defined as tools that aim to introduce and suggest products to users. The suggestion process depends on many factors, such as user behavior and product similarity. In recent years, many research papers have discussed recommendation systems and introduced new solutions and methods to build them. On the other hand, in the last few years, data representation has also become an important issue. Because of the massive increase in data, new methods to represent data have been introduced and adopted, such as graph-based data representation. In this work, the efficiency of employing graph-based databases in building recommendation systems was evaluated and compared to traditional approaches.. Specifically, Amazon Product Reviews dataset was used to build a recommendation system using traditional methods. This data was then transformed to a graph format and used to generate recommendations. Metrics such as accuracy, recall, and precision were adopted to determine the efficiency and accuracy of the results, as will be discussed later.
Synergy of Technology and Agriculture through the Development of a Web-Based Expert System for Cocoa Disease Diagnosis Using the Certainty Factor Method Kevin Yanto; Musdalifa; Moh Ali Akbar A Dg Matona; Juni Wijayanti Puspita
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.9986

Abstract

Cocoa (Theobroma cacao L.) is one of the leading agricultural commodities that plays a vital role in Indonesia’s economy. However, its productivity is often hindered by pest and disease attacks. On the other hand, the limited availability of agricultural experts and the difficulties faced by farmers in accessing guidance and information regarding plant diseases highlight the urgent need for a system that can assist in identifying problems quickly and accurately. This study aims to develop a web-based expert system capable of diagnosing pests and diseases in cocoa plants using the Certainty Factor (CF) method. The system incorporates data on 9 types of diseases and 6 types of pests along with their symptoms. Diagnosis is performed by calculating certainty values based on a combination of expert confidence and user input using CF formulas. With a web-based interface, the system can be easily accessed by farmers via the internet. The diagnostic results of this system show a similarity rate of 93.33% with those of other studies. This finding indicates that the CF approach demonstrates competitive performance. Therefore, this system has the potential to serve as an effective tool in supporting cocoa plant health management by farmers.Keywords: Disease diagnosis, Cocoa, Certainty factor method, Web-based expert system
Modified Genetic Algorithm in Isotropic Semivariogram Modeling: A Case Study of Groundwater Level in Kalimantan Peatland Kurnia Novita Sari; Ari Ratna Gumilang; Muhammad Rozzaq Hamidi; Anwar Efendi Nasution; Giraldi Fardiaz Kuswanda
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.10021

Abstract

The purpose of this study is to develop a method to estimate semivariogram parameters using genetic algorithm (GA). GA is a numerical method that has been extensively applied. GA is applicable to estimate semivariogram parameters including constraint based on the parameters. The modification that applied to GA shows better performance than iterative least square (ILS). The application of spatial analysis to groundwater level (GWL) in peatland areas is still limited, especially semivariogram analysis. Thus, the m-GA (modified-GA) is applied to GWL in Kalimantan peatland and then compared with ILS. The study shows that the spherical semivariogram model estimated using the m-GA provides the best performance, because both the model and kriging have the lowest root mean square error (RMSE) values, at and , respectively. The combination of spherical semivariogram model with the m-GA produces optimal and accurate semivariogram parameters to support kriging interpolation on GWL peatland.
An experiment using the Haar-Cascade and LBPH algorithms for real-time recognition of multiple faces in a single frame. Dyah Anggun Sartika; Denny Hardiyanto; Hanum Arrosida
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.10041

Abstract

Face recognition is an important field in digital image processing and artificial intelligence that is widely applied in security systems, automatic attendance, and human-computer interaction. This research aims to develop and test a real-time multiple face recognition system using a combination of the Haar Cascade algorithm for face detection and the Local Binary Pattern Histogram (LBPH) for face recognition. The system is implemented using the Python programming language and the OpenCV library, and tested under various conditions, such as variations in lighting, face viewing angles, and the number of faces in one frame. Test results show that the system is able to recognize multiple faces with approximately 90% accuracy under normal lighting conditions with varying distances, and maintains performance above 80% under low lighting conditions or side-facing face angles. The average detection and recognition time per face ranges from 40–60 milliseconds, which still supports real-time performance. Compared with deep learning-based approaches, this system has advantages in terms of efficiency and ease of implementation, especially on devices with limited specifications. This study shows that the combination of Haar Cascade and LBPH is still relevant and effective for light- to medium-scale multiple face recognition applications. Keywords: Multiple faces, Haar Cascade, Face recognition, LBPH
A Smart Decision Model for MSME Investments on Islamic Fintech Platforms: Integrating PSI and SWOT Methods Esa Kurniawan; Imam Fathurahman; Novira Dian Antasari
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.10067

Abstract

The rapid growth of Islamic financial technology (fintech) has opened new opportunities for micro, small, and medium enterprises (MSMEs) to access capital. However, investment decision-making remains complex due to diverse risk and return profiles. This study aims to develop a smart investment decision model for MSMEs on Islamic fintech platforms by integrating the Preference Selection Index (PSI) and Strengths, Weaknesses, Opportunities, and Threats (SWOT) methods. Primary data were collected from 30 MSMEs engaged in Islamic fintech funding within the Greater Jakarta area and from 116 users of Islamic fintech platforms serving as respondents. The PSI method was applied to rank MSMEs based on five criteria, return on investment, business risk, capital needs, Sharia compliance, and platform reputation. Results show that Business Risk and Sharia Compliance are the most influential factors determining investment eligibility. The SWOT analysis identified strong platform transparency and Sharia adherence as internal strengths, alongside challenges related to repayment flexibility and financial literacy. Integrating PSI and SWOT produced a comprehensive, Sharia-aligned decision-support framework that enhances objectivity, accuracy, and transparency in MSME funding evaluations. The findings offer actionable insights for investors, fintech operators, and policymakers to strengthen ethical, inclusive, and sustainable Islamic digital finance ecosystems.
Comparative Analysis of Digital Artifacts in Two Versions of Cellebrite Physical Analyzer (V7.62 and V7.73) Against UFED Extraction Results from Android Devices Setyadi Ari Murtopo; Himmatul Husna; Sonny Kristianto
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 2 (2025): Vol. 11 No. 2 Dec 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i2.10102

Abstract

The fragmentation of the Android system and constant app updates create significant challenges in digital forensics. The urgency of this study is to empirically verify whether upgrading forensic tools, specifically from Cellebrite Physical Analyzer (CPA) v7.62 to v7.73, provides significant decoding value to prevent the loss of critical evidence. This study compares the effectiveness of both CPA versions on File System Extraction from OPPO (ColorOS) and Infinix (XOS) devices. Identical extraction images were processed by both CPA versions, and the results were analyzed quantitatively. The results show that CPA v7.73 is collectively superior, finding more artifacts. The most dramatic improvement occurs on Infinix (XOS) (35.69%), with crucial discoveries such as +7,296 additional Contacts and +368 Call Logs, demonstrating the success of the v7.73 decoder in overcoming the unique XOS database. On OPPO devices, improvements focused on communication with +966 additional WhatsApp Messages. This study concludes that CPA v7.73 is indispensable in forensic practice, as failure of older versions in recovering core artifacts can lead to substantial loss of evidence and affect the validity of investigations.

Page 2 of 2 | Total Record : 17