JITSI : Jurnal Informatika Dan Teknologi Sistem Informasi
JITSI: Jurnal Informatika dan Teknologi Sistem Informasi merupakan jurnal ilmiah yang diterbitkan sebagai media publikasi hasil penelitian, kajian ilmiah, dan pengembangan ilmu pengetahuan di bidang informatika, teknologi informasi, dan sistem informasi. Jurnal ini bertujuan menjadi wadah bagi akademisi, peneliti, praktisi, mahasiswa, serta profesional untuk menyebarluaskan hasil penelitian yang berkualitas, inovatif, dan memberikan kontribusi terhadap perkembangan ilmu pengetahuan maupun penerapannya dalam masyarakat. Ruang lingkup publikasi JITSI meliputi berbagai bidang, antara lain Rekayasa Perangkat Lunak, Sistem Informasi, Kecerdasan Buatan (Artificial Intelligence), Machine Learning, Data Mining, Big Data, Data Science, Internet of Things (IoT), Keamanan Siber, Komputasi Awan (Cloud Computing), Jaringan Komputer, Multimedia, Mobile Computing, Sistem Pendukung Keputusan, Geographic Information System (GIS), Blockchain, Human-Computer Interaction (HCI), Teknologi Web, Basis Data, serta topik lain yang relevan dengan perkembangan informatika dan teknologi sistem informasi.
Articles
18 Documents
<![CDATA[PENERAPAN ALGORITMA APRIORI UNTUK IDENTIFIKASI POLA KETERKAITAN PEMINJAMAN BUKU PADA PERPUSTAKAAN STMIK MULIA DARMA ]]>
<![CDATA[CHANDRA FRENKI SIANTURI]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.123
<![CDATA[Libraries generate borrowing transaction data that can be utilized to identify relationships among books frequently borrowed in the same transaction. This study applies the Apriori algorithm to identify patterns of relationships among book-borrowing transactions at the STMIK Mulia Darma Library. The research stages include data selection, data cleaning, transformation into a transaction basket format, frequent itemset generation, association rule generation, and evaluation using support, confidence, and lift ratio. Since the available research files do not contain actual borrowing transaction data from the STMIK Mulia Darma Library, the quantitative results reported in this study use 360 anonymous/simulated test transactions to verify the analysis mechanism. Under the main scenario, with a minimum support of 5% and a minimum confidence of 70%, the algorithm generates 50 frequent itemsets and 39 association rules with a lift ratio greater than one. Testing six combinations of threshold values shows that increasing the minimum support and minimum confidence reduces the number of patterns, making the resulting rules more selective. The verification results indicate that the Apriori algorithm can be used to transform borrowing records into information about relationships among library collections, which can support shelf arrangement, reading recommendations, and collection acquisition planning. The numerical results must be replaced or validated using official data before being used as a basis for library decision-making.]]>
<![CDATA[DATA MINING PENJUALAN SUKU CADANG MOBIL MENGGUNAKAN ALGORITMA APRIORI PADA PT. ISUINDOMAS PUTRA ]]>
<![CDATA[Eferoni ndruru]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.124
<![CDATA[Competition in the business world, particularly in the automotive spare parts sales industry, is becoming increasingly intense, requiring businesses to develop marketing strategies to increase sales. The growing volume of daily sales data can be utilized to develop effective marketing strategies when properly processed and analyzed. Sales of automotive spare parts increase every month, with a wide variety of products offered to attract customers. To identify the products with the highest sales, the Apriori algorithm can be applied with the assistance of the Tanagra software. This approach enables businesses to identify the best-selling products based on sales transaction data. The Apriori algorithm is a type of association rule in data mining. One of the key stages in association analysis that has attracted considerable research interest is frequent pattern mining, which aims to generate efficient algorithms for identifying frequently occurring itemsets. The significance of an association rule can be determined using two main measures: support and confidence. Support represents the percentage of transactions in the database containing a particular item combination, while confidence measures the strength of the relationship between items in an association rule. By applying the Apriori algorithm, businesses can identify purchasing patterns and develop more effective marketing strategies to improve sales performance]]>
<![CDATA[OPTIMALISASI DALAM PEMBERIAN PINJAMAN KEPADA ANGGOTA DENGAN MENERAPKAN METODE MABAC ]]>
<![CDATA[Fince Tinus Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.125
<![CDATA[Targeted loan disbursement is an important factor in maintaining the stability and sustainability of credit unions. CU. Makmur Sejahtera, as a savings and loan cooperative, requires an objective and systematic approach to determining the eligibility of members for loan approval. This study aims to optimize the loan disbursement process by implementing the Multi-Attributive Border Approximation Area Comparison (MABAC) method. Five criteria are used in the decision-making process: savings amount, membership duration, monthly income, loan history, and asset collateral. The MABAC method is employed to calculate the score of each alternative based on the deviation of its values from the Border Approximation Area (BAA), thereby generating a fair and data-driven final ranking. The results indicate that this method can identify the most eligible members for loan approval while promoting transparency in the selection process. The implementation of the MABAC method can serve as an effective solution for supporting multicriteria decision-making in cooperatives.]]>
<![CDATA[ANALISA PRESTASI MAHASISWA MENGGUNAKANJARINGAN SARAF TIRUAN METODE BACKPROPAGATION ]]>
<![CDATA[Indra Sidabutar Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.126
<![CDATA[Students’ academic performance can serve as an indicator to support the monitoring of learning processes and the provision of early academic assistance. This study applies an Artificial Neural Network (ANN) using the Backpropagation algorithm to predict students’ cumulative Grade Point Average (GPA) at the end of the fourth semester based on Semester 1 to Semester 3 GPAs, the percentage of credits successfully completed, and the number of repeated courses. The data were processed through selection, anonymization, and cleaning, followed by partitioning into 70% for training, 15% for validation, and 15% for testing. The data were also normalized to a range of 0.1–0.9 using parameters calculated exclusively from the training set. Nine combinations of hidden-layer architectures and learning rates were evaluated, with each configuration tested five times using different random seeds. Since the available research files did not contain actual academic records, the quantitative results reported in this study were obtained using 320 anonymized/simulated test records to verify the experimental procedure rather than to establish empirical findings for Universitas Budi Darma. The 5-5-1 architecture with a learning rate of 0.10 achieved the lowest average validation RMSE of 0.119 ± 0.009. On the test dataset, the selected model achieved an MSE of 0.0162, an RMSE of 0.1274, an MAE of 0.1035, and an R² of 0.9415. The verification results indicate that Backpropagation can model nonlinear relationships among academic indicators. However, operational implementation requires further validation using official academic records.]]>
<![CDATA[ANALISIS POLA PENGELUARAN OBAT MENGGUNAKAN ALGORITMA FP-GROWTH SEBAGAI PENDUKUNG PENGENDALIAN PERSEDIAAN PADA RS ESTOMIHI ]]>
<![CDATA[Moch.Iswan Perangin-Angin Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.127
<![CDATA[Drug inventory control requires information on patterns of drug co-occurrence in healthcare service transactions. This study applies the FP-Growth algorithm to identify frequent itemsets and association rules in drug dispensing data to support inventory control at Estomihi Hospital. The research stages include data preprocessing, FP-Tree construction, frequent itemset discovery, and rule evaluation using support, confidence, and lift ratio. Testing using 360 simulated transactions with a minimum support of 5% and a minimum confidence of 60% generated 38 frequent itemsets and 46 association rules with lift values greater than 1. The results indicate that increasing the minimum support and confidence thresholds reduces the number of generated patterns. FP-Growth has the potential to help identify groups of drugs that require joint monitoring. However, the simulation-based results do not reflect the hospital's actual conditions; therefore, their practical application requires validation using official transaction data.]]>
<![CDATA[IMPLEMENTASI NAIVE BAYES UNTUK MENGANALISIS SENTIMEN CAPRES 2024 PRABOWO SUBIANTO BERBASIS MACHINE LEARNING ]]>
<![CDATA[Saidi Ramadan Siregar Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.128
<![CDATA[Targeted loan disbursement is an important factor in maintaining the stability and sustainability of credit unions. CU. Makmur Sejahtera, as a savings and loan cooperative, requires an objective and systematic approach to determining the eligibility of members for loan approval. This study aims to optimize the loan disbursement process by implementing the Multi-Attributive Border Approximation Area Comparison (MABAC) method. Five criteria are used in the decision-making process: savings amount, membership duration, monthly income, loan history, and asset collateral. The MABAC method is employed to calculate the score of each alternative based on the deviation of its values from the Border Approximation Area (BAA), thereby generating a fair and data-driven final ranking. The results indicate that this method can identify the most eligible members for loan approval while promoting transparency in the selection process. The implementation of the MABAC method can serve as an effective solution for supporting multicriteria decision-making in cooperatives.]]>
<![CDATA[MODIFIKASI METODE CHINESE REMINDER THEOREM MENGGUNAKAN BLUM BLUM SHUB GENERATOR UNTUK PEMBENTUKAN WATERMARKING CITRA DIGITAL ]]>
<![CDATA[Soeb Aripin Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.129
<![CDATA[Data security is an essential aspect of information technology development, particularly in the exchange and distribution of digital information. Digital images, especially personal photographs, are vulnerable to misuse by unauthorized parties. One technique that can be used to enhance information security in digital images is watermarking, which involves embedding specific information into an image as a means of data protection. The Chinese Remainder Theorem (CRT) is one of the methods that can be applied in the watermark embedding process. However, the application of this method may pose security risks if the embedding pattern can be identified by unauthorized parties. Therefore, modifications are needed to improve the security of the watermark embedding process. This study aims to modify the CRT method by integrating the Blum Blum Shub Generator (BBS) algorithm to randomize data embedding locations in digital images. The BBS algorithm is used to generate random numbers that serve as the basis for determining pixel positions where the watermark is embedded. This approach makes the embedding locations more difficult to predict, thereby reducing the risk of watermark detection and extraction by unauthorized parties. This modification is expected to enhance watermark embedding security while preserving the visual imperceptibility of the image, ensuring that the changes are not easily noticeable to the naked eye. Thus, the combination of the CRT method and the BBS algorithm is expected to provide an alternative approach to improving the protection of information embedded in digital images]]>
<![CDATA[IMPLEMENTASI LAGGED FIBONACCI GENERATOR PADA PROSES PEMBANGKITAN KUNCI ALGORITMA ONE TIME PAD (OTP) ]]>
<![CDATA[Taronisokhi Zebua Waruwu]]>
<![CDATA[ Interaksi : Jurnal Informatika Dan Teknologi Sistem Informasi Vol 1 No 01 (2024): Mei ]]>
Publisher : <![CDATA[PT. Ndruru Jaya Mandiri ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.67763/jitsi.v1i01.130
<![CDATA[The effectiveness of the key used in a data security algorithm is one of the essential aspects that must be considered when implementing data security techniques. Many data security algorithms, particularly classical cryptographic algorithms, still employ key generation techniques that are not sufficiently optimized to ensure data security. As a result, secured data or information can be easily accessed by unauthorized parties. Key resistance to attacks is a fundamental requirement in cryptographic techniques for protecting data against various forms of attacks. Resistance to data attacks does not depend solely on the complexity of the cryptographic algorithm used but is also significantly influenced by the optimization of the key to support the objectives of data security. One technique that can be used to generate more effective keys is random key generation, in which the keys are designed to be unpredictable so that the patterns of the keys used to secure data are difficult for attackers to identify. One approach that can be employed is random number generation, which can be used to produce keys with unpredictable patterns and no easily identifiable relationships. The Lagged Fibonacci Generator algorithm is one of the variants of random number generation algorithms. The application of this algorithm in generating keys for cryptographic algorithms is expected to improve the effectiveness of the algorithms used to encrypt and decrypt confidential data or information.]]>
