Article Per Year (5 Year)
p-Index From 2021 - 2026
1.126
P-Index
This Author published in this journals
All Journal JTT (Jurnal Teknologi Terpadu) JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Computer Science and Information Technologies SKANIKA: Sistem Komputer dan Teknik Informatika INTERNAL (Information System Journal) ISTEK
Ichsan Taufik, Ichsan
Jurusan Teknik Informatika, Fakultas Sains dan Teknologi Universitas Islam Negeri Sunan Gunung Djati Bandung
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology Mechanical Engineering Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Vector space model, term frequency-inverse document frequency with linear search, and object-relational mapping Django on hadith data search Taufik, Ichsan; Agra, Agra; Gerhana, Yana Aditia
Computer Science and Information Technologies Vol 5, No 3: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v5i3.p306-314

Abstract

For Muslims, the Hadith ranks as the secondary legal authority following the Quran. This research leverages hadith data to streamline the search process within the nine imams’ compendium using the vector space model (VSM) approach. The primary objective of this research is to enhance the efficiency and effectiveness of the search process within Hadith collections by implementing pre-filtering techniques. This study aims to demonstrate the potential of linear search and Django object-relational mapping (ORM) filters in reducing search times and improving retrieval performance, thereby facilitating quicker and more accurate access to relevant Hadiths. Prior studies have indicated that VSM is efficient for large data sets because it assigns weights to every term across all documents, regardless of whether they include the search keywords. Consequently, the more documents there are, the more protracted the weighting phase becomes. To address this, the current research pre-filters documents prior to weighting, utilizing linear search and Django ORM as filters. Testing on 62,169 hadiths with 20 keywords revealed that the average VSM search duration was 51 seconds. However, with the implementation of linear and Django ORM filters, the times were reduced to 7.93 and 8.41 seconds, respectively. The recall@10 rates were 79% and 78.5%, with MAP scores of 0.819 and 0.814, accordingly.
IMPLEMENTASI FP-GROWTH DAN FUZZY TSUKAMOTO UNTUK MENENTUKAN PERSENTASE KUOTA JALUR MASUK PERGURUAN TINGGI Khairunnisa, Nafa; Jumadi, Jumadi; Taufik, Ichsan
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 8 No 1 (2025): Jurnal SKANIKA Januari 2025
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v8i1.3337

Abstract

Every university strives to achieve or maintain excellent accreditation. Students who graduate with a satisfactory predicate play an important role in determining the accreditation. According to BAN-PT 2021, a university is considered excellent if it has students with a maximum study period of 4.5 years and an average GPA ≥ 3.25. One way to maintain it is to optimally manage the distribution of quotas for the New Student Admission (PMB) entrance pathway. This study aims to investigate how the variables of GPA, study period, and entry path in the data of graduates relate to each other. To get the association pattern between these variables, FP-Growth is used. Furthermore, the percentage of quota distribution is calculated using Fuzzy Tsukamoto. From this research, the accuracy of the model is 94.42% and the precision value is 62.5%, which indicates that the method used is effective in helping determine the optimal quota distribution for PMB. Thus, these results can be used to support university policies in determining a more appropriate quota distribution to support the achievement of superior accreditation.
Klasifikasi Penyakit Daun Kopi Arabika Berbasis Gambar Menggunakan Model Convolutional Neural Networks DenseNet121 Solehudin, Muhammad Alwy; Gerhana, Yana Aditia; Taufik, Ichsan
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6407

Abstract

Detection of Arabica coffee leaf diseases is crucial for improving the quality and yield of coffee crops. This study aims to apply the DenseNet121 Convolutional Neural Network model to identify three types of diseases on Arabica coffee leaves, namely Rust, Phoma, and Miner. The data used consists of images of Arabica coffee leaves, which are divided into training, validation, and test sets. The model was trained using the Adamax optimizer with hyperparameters such as a maximum of 30 epochs and a batch size of 32. During training, the model achieved a validation accuracy of 98.86% before being stopped by the early stopping callback at epoch 28 to prevent overfitting. Model evaluation using a confusion matrix resulted in 97% accuracy on the test data, with excellent precision, recall, and F1-score values for most categories, particularly for the Healthy, Miner, and Phoma classes. The Rust class showed lower recall due to data imbalance in the test set. The results of this study demonstrate that the DenseNet121 model is reliable for detecting diseases on Arabica coffee leaves with high accuracy and provides an important contribution to the technology of plant health monitoring, which can assist farmers in early detection and improve coffee crop productivity.
Klasifikasi Citra Ras Kucing Berbasis CNN dengan Metode MobileNet-V2 Hermawan, Ramadhan Anugrah; Taufik, Ichsan; Aditia Gerhana, Yana
INTERNAL (Information System Journal) Vol. 8 No. 1 (2025)
Publisher : Masoem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/internal.v8i1.1390

Abstract

This study evaluates the performance of a Convolutional Neural Network (CNN) using the MobileNet-V2 architecture in classifying four cat breeds. The lack of public understanding in distinguishing cat breeds, especially due to the prevalence of mixed breeds, presents a significant challenge in accurate identification. The model was tested across multiple epochs to observe training and validation accuracy, aiming to assess its effectiveness and stability. Experimental results show that the highest validation accuracy of 93.81% was achieved at epoch 90. Although the model performed well, further optimization is needed to address overfitting and improve generalization capability. This research contributes to the development of an automated breed identification system that can be applied in education, adoption processes, and veterinary healthcare.
Implementasi Teknologi Blockchain dalam Pengembangan Aplikasi Web Terdesentralisasi untuk Pengelolaan Data Pos Pelayanan Terpadu: Studi Kasus: Posyandu Mawar Lingkungan Gibug Qomaruddin, Nurhadi; Gerhana, Yana Aditia; Taufik, Ichsan; Slamet, Cepy; Firdaus, Muhammad Deden
ISTEK Vol. 14 No. 1 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i1.2112

Abstract

The Integrated Service Post (Posyandu) is a community-based health service established by the government, playing an important role in monitoring child health, including efforts to reduce infant and child mortality rates. However, data management at Posyandu is generally still conducted manually using paper-based records, making it prone to data loss and inefficient in terms of access and tracking. One common approach to overcoming these challenges is the use of distributed data systems, which allow data storage and processing to occur across multiple computers in different locations. Nevertheless, many of these systems still rely on centralized servers, making them vulnerable to data breaches and manipulation due to the single point of storage. To address this issue, this research proposes the development of a decentralized web application based on blockchain technology as a solution for secure, transparent, and traceable data management. The application is developed using smart contracts written in Solidity, deployed on the Ethereum blockchain, with Hardhat as the backend framework and React.js as the user interface. The system was developed using a prototyping methodology and evaluated through black-box testing to assess its functional performance. Test results show that the application is capable of managing data effectively, while maintaining a high level of security and transparency. By adopting blockchain technology, the system enhances the effectiveness and efficiency of Posyandu’s data management, while ensuring data integrity and traceability within a decentralized environment.
Price Prediction of Second-Hand Iphones Using Random Forest Regression Based on Unit Conditions Anggayana, Denta Pratama; Taufik, Ichsan; Gerhana, Yana Aditia
ISTEK Vol. 14 No. 1 (2025)
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v14i1.2154

Abstract

This study presents the development of a price prediction model for second-hand Iphones based on unit conditions using the Random Forest Regression algorithm, implemented in a web-based application. A dataset of 542 records was collected from Facebook Marketplace and iPhone trading groups, with variables including Iphone type, storage capacity, warranty status, Face ID, and Truetone. The research employed the CRISP-DM methodology through the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The model was tested using data splits of 80%–20%, 70%–30%, and 60%–40%, resulting in MAE values of 8.32%–8.42% and RMSE values of 10.64%–10.88%, indicating good and consistent accuracy. The developed system can automatically provide price recommendations based on unit conditions, assisting both sellers and buyers in determining fair market prices.
Rekognisi Tulisan Kaligrafi Dengan Menggunakan Metode Convolutional Neural Network Arsitektur MobileNetv2 Irhamnillah, Sami; Atmadja, Aldy Rialdy; Taufik, Ichsan
Jurnal Teknologi Terpadu Vol 13, No 2 (2025): JTT (Jurnal Terpadu Terpadu)
Publisher : Pusat Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32487/jtt.v13i2.2616

Abstract

This research aims to develop an automatic classification model to recognize the type of Arabic calligraphy writing using MobileNetV2 Convolutional Neural Network (CNN) architecture. Arabic calligraphy has a visual uniqueness and complexity of letterforms that become a challenge in the classification process, especially for ordinary people. The four main calligraphy types used in this research are Tsulust, Naskhi, Diwani, and Kufi. The research follows the CRISP-DM stages which include business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset used is the HICMA dataset consisting of 5,031 calligraphy images. The data is processed through cropping, normalization, and resizing to 224x224 pixels. The model was trained with epoch variations (10, 20, 30, and 40) to obtain the best configuration. The results show that the model at the 20th epoch has the most optimal performance with a testing accuracy of 97.52%. Evaluation of classification metrics showed high F1-Score values in the majority classes. The previously low-performing Kufi class was improved through data augmentation techniques to obtain an F1-Score value of 0.99. The model is then integrated into a Flask-based web application that allows users to upload images and receive classification results directly. The results of this research show that MobileNetV2 is effective for Arabic calligraphy type classification and can be practically implemented for educational purposes as well as digital preservation of Islamic culture.
Co-Authors Aditia Gerhana, Yana Agra, Agra Aldy Rialdy Atmadja Anggayana, Denta Pratama Cepy Slamet Firdaus, Muhammad Deden Hermawan, Ramadhan Anugrah Irhamnillah, Sami Jumadi Jumadi Khairunnisa, Nafa Qomaruddin, Nurhadi Solehudin, Muhammad Alwy Yana Aditia Gerhana, Yana Aditia