cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
jatilima
Contact Email
jatilima30@gmail.com
Phone
+6285359150140
Journal Mail Official
jatilima30@gmail.com
Editorial Address
Cattleya Darmaya Fortuna (CDF) Marindal 1, Pasar IV Jl. Karya Gg. Anugerah Kecamatan. Patumbak, Medan - Sumatera Utara
Location
Kab. deli serdang,
Sumatera utara
INDONESIA
Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Published by Cattleya Darmaya Fortuna
ISSN : -     EISSN : 27211800     DOI : -
Core Subject : Science,
Computer Science & IT
JATILIMA merupakan jurnal yang terbit dua nomor dalam satu volume (tahun), yaitu Peridoe I Bulan April dan Periode II Bulan Oktober. JATILIMA mempublikasikan tulisan-tulisan ilmiah hasil pemikiran, studi literatur, dan penelitian dalam bidang Ilmu Komputer. JATILIMA merupakan jurnal dengan sistem review yang merupakaan aspek penting dalam penyebaran ilmu pengetahuan.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 196 Documents
 16   17   18   19   20 
Classification of Hijab Types Based on Gray Level Co-occurrence Matrix Features and the K-Nearest Neighbor (KNN) Algorithm Faradita, Nazwa Alya; M. Fakhriza
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1737

Abstract

This study aims to build an automatic classification system to address the challenge of visually identifying hijab types by utilizing digital image processing technology. The research scope is limited to two categories: pashmina and instant hijabs. The applied method involves the Gray Level Co-occurrence Matrix (GLCM) to extract texture features in four angular directions, which yields four primary feature values: Contrast, Energy, Correlation, and Homogeneity. These features are subsequently classified using the K-Nearest Neighbor (KNN) algorithm with the Euclidean Distance metric. The dataset used consists of 60 image samples, divided into 48 training data and 12 test data. Testing was conducted with varying K-values (1, 3, 5, and 7). The results show that the classification system using the GLCM and KNN combination is effective, achieving a peak accuracy of 83.33% at K-values of 3, 5, and 7. This outcome confirms the capability of GLCM-extracted texture features to distinguish between the two hijab types and highlights the potential application of this system in the field of Muslim fashion.
THE USE OF THE AHP AND TOPSIS METHODS IN ANALYZING THE SELECTION OF THE BEST CRYPTO (CASE STUDY: BITCOIN AND SOLANA) Anggraini, Arizka; Hasugian, Abdul Halim
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1757

Abstract

The development of digital financial technology has introduced a variety of crypto assets with different characteristics and mechanisms, necessitating an objective analytical approach to determine the most optimal asset. This research aims to identify the best crypto between Bitcoin and Solana by considering five main criteria: transaction speed, transaction cost, energy consumption, network security, and network stability. The approach used is descriptive quantitative with the application of the Analytic Hierarchy Process (AHP) method to determine the weight of each criterion and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to rank the alternatives based on the obtained weights. Data was collected through a literature review and official sources from each crypto platform to ensure the validity and reliability of the results. Based on the analysis, Solana obtained the highest preference value as it showed significant superiority in transaction speed, cost efficiency, and low energy consumption, while Bitcoin remains superior in the aspect of more assured network security and stability. The combination of the AHP and TOPSIS methods proved capable of producing a systematic, rational, and measurable multi-criteria decision-making process. The results of this study have implications for the development of a data-driven digital asset evaluation model, which can serve as a reference for investors, market analysts, and researchers in conducting comparative assessments of crypto asset performance more efficiently, transparently, and based on empirical evidence, in line with the increasing need for analytical instruments in modern financial technology investment.
Application of Mixed Integer Linear Programming (MILP) Method in Capacity Vehicle Routing Problems in Heterogeneous Fleets (HFCVRP) at Bagol Hydroponics UMKM Ditta Arsyilviasari; Ismail Husein
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1765

Abstract

Due to variations in vehicle capacity, Bagol Hydroponics UMKM has trouble figuring out cost-effective and distance-efficient product distribution routes. For this reason, this study uses the Mixed Integer Linear Programming (MILP) approach to solve the Heterogeneous Fleet Capacitated Vehicle Routing Problem (HFCVRP). This study is a quantitative applied research project that uses distance data from the Google Maps API to create a mathematical model and the best distribution route using IBM ILOG CPLEX software. The MILP model is designed to decrease the overall distance driven by automobiles while taking sub-trip elimination and vehicle capacity limitations into account. The results demonstrate that the MILP model can provide optimal distribution routes with efficient calculation time and an average distance savings of 1.74% when compared to current routes. Therefore, it has been demonstrated that applying the MILP approach to the HFCVRP problem improves the distribution efficiency of Bagol Hidroponik UMKM products. This can serve as a guide for other UMKM in order to create the most efficient delivery routes.
Application of SMOTE Random Forest Classification and Gradient Boosting on Imbalanced Tuberculosis Data Mutiara Amanda; Ismail Husein
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1767

Abstract

Tuberculosis (TB) is an infectious disease that remains a serious problem in Indonesia due to its spread and imbalanced data in cases. This study aims to compare the performance of Random Forest and Gradient Boosting algorithms in classifying tuberculosis in imbalanced data. The methods used include the application of the Synthetic Minority Oversampling Technique (SMOTE) as a data balancing method, as well as model evaluation using the metrics of accuracy, precision, sensitivity, specificity, and AUC. The results show that Gradient Boosting without SMOTE produces the best performance with an accuracy of 93% and an AUC of 0.91, while the application of SMOTE actually reduces the performance of the model. Meanwhile, Random Forest showed stable results in both conditions with an accuracy of 93% and an AUC of 0.89. Thus, it can be concluded that Gradient Boosting without SMOTE provides the most optimal classification results and can be the basis for developing classification methods for Imbalanced Data in tuberculosis. Abstract is a brief representation of the whole article which contains the context of the problem (background), the purpose of the research, the principal methods, the results and the major conclusion (contribution). An abstract is often presented separately from the article, so it must be able to stand alone. Thus, the reference must be avoided. Abstract must be written in Nunito , with no more than 300 words in one paragraph.
The Influence of Computer Technology in Improving Learning Effectiveness at Imelda University Medan Khairunnisa; Sari, Ika Yusnita; Rahmi, Elvika; Marpaung, Astrida N; Lumbanbatu, Maristella J
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v6i03.1179

Abstract

This study aims to analyze the impact of computer technology usage in improving the effectiveness of learning at Universitas Imelda Medan. Based on data collected through surveys and interviews with lecturers and students, it was found that the use of computer technology significantly affects students' learning outcomes. The majority of respondents acknowledged that computer technology, such as the use of educational software, e-learning platforms, and multimedia applications, helps them better and more quickly understand the subject matter. Survey results showed that 85% of students feel more engaged and motivated to learn when using computer technology. Additionally, 75% of lecturers reported that computer technology allows them to teach more effectively, particularly in presenting complex material through visual and interactive means. However, challenges such as limited computer facilities and internet connection issues have become major obstacles in implementing this technology. The study concludes that while computer technology provides many benefits in enhancing learning effectiveness, improvements in facilities and training for lecturers are needed to maximize the use of technology in education
Application of the SAW Method in the Decision Support System for Employee Performance Assessment at PT. Sarma Amarise Anugerah Sejahtera Naibaho, Eltrina
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v6i03.1186

Abstract

Employee performance appraisal is an important aspect of human resource management, but it often faces challenges related to subjectivity and inaccuracies. PT. Sarma Amarise Anugerah Sejahtera faces this problem in its manual and less objective performance assessment system. This study aims to design and implement a decision support system based on the Simple Additive Weighting (SAW) method to improve objectivity, efficiency, and accuracy in employee performance assessment. The SAW method is used to evaluate performance based on various criteria, by giving weight to each relevant criterion. The results of this system are expected to provide more transparent and accountable decisions, as well as assist management in planning the right development and policies for employees. The results of the study show that the application of the SAW method in employee performance assessment at PT. Sarma Amarise Anugerah Sejahtera can improve the quality of decision-making and minimize the bias that usually appears in manual assessment systems.
Sentiment Analysis of Gojek App Reviews on Google Play Store with Natural Language Processing Using Naive Bayes' Algorithm Rahman, Zumardi; Sakinah, Putri; Hendra, Yomei; Satria, Budy; Maulana, Fajar; Ayun, Aisyah Qurrata
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v6i03.1189

Abstract

In the digital era, sentiment analysis is an important tool to understand user perceptions of applications, including the Gojek application. This study aims to analyze the sentiment of Gojek application user reviews on the Google Play Store using the Naive Bayes algorithm. The research process involved collecting 5,000 reviews, preprocessing the text, weighting with TF-IDF, and applying the Naive Bayes algorithm to classify sentiment into negative, neutral, and positive. The evaluation results show that the model has the best accuracy of 76% after applying the data balancing technique. The model's performance for negative sentiment is very good with a precision of 91% and an F1 score of 87%. Positive sentiment shows quite good performance with a precision of 76% and an F1 score of 65%. However, neutral sentiment has low precision (23%) although recalls increased to 51%. Sampling techniques such as SMOTE have succeeded in improving the model's ability to recognize underrepresented classes. With an overall evaluation of weighted average precision of 82% and an F1 score of 78%, this model is considered quite reliable in analyzing the sentiment of Gojek app reviews. This research provides insights for application developers in improving service quality based on user perception..
Application of Data Mining Method to Predict Soil Quality Based on Environmental Parameters Marsya, Jiwa Malem
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v6i03.1190

Abstract

Employee performance appraisal is an important aspect of human Soil quality is a critical factor in agriculture and environmental conservation, as it directly impacts agricultural productivity and ecosystem sustainability. Traditional methods of monitoring and evaluating soil quality based on environmental parameters, such as pH, moisture content, temperature, and humidity, can be time-consuming and costly. This research aims to explore the application of data mining techniques to predict soil quality using various environmental parameters. Data mining, particularly machine learning algorithms such as decision trees, support vector machines (SVM), and neural networks, allows for the extraction of hidden patterns and relationships in large datasets, providing an efficient approach for soil quality prediction. The study utilizes data from soil samples, including parameters like pH, moisture content, temperature, and other environmental variables, to develop predictive models. The effectiveness of different data mining techniques is evaluated based on their accuracy and efficiency in predicting soil quality. The results of this study are expected to contribute to the development of reliable and rapid tools for assessing soil quality, which could be applied in agricultural management, land conservation, and environmental monitoring.By leveraging data mining techniques, this research provides insights into the potential for improving soil management practices and supporting sustainable agriculture. The findings of this study may offer valuable recommendations for farmers, land managers, and environmentalists in making informed decisions for better land use and conservation strategies.
Digital Forensic Approaches for Counterfeit Money Detection: A Compratie of KNN, Logistic Regression, and SVM Classifiers Sabrina Nur Amalia; Imam Yuadi
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1764

Abstract

Counterfeit currency presents a substantial risk to economic stability and financial security, necessitating efficient and dependable detection techniques in both forensic and practical contexts. This research examines digital forensic methodologies for the identification of counterfeit banknotes employing three machine learning classifiers: K-Nearest Neighbors (KNN), Logistic Regression, and Support Vector Machine (SVM). A dataset was generated by photographing authentic and counterfeit Indonesian banknotes using a mobile phone camera, thereafter undergoing preprocessing and augmentation to enhance resilience. To improve classification performance, three image preprocessing techniques—grayscale filtering, edge detection, and blurring—were employed. The models were assessed based on accuracy, precision, recall, and F1-score obtained from confusion matrix analysis. The experimental findings demonstrated that SVM and Logistic Regression consistently surpassed KNN in all settings, with SVM attaining the best overall accuracy of 0.997 under gray and blur filtering. Logistic Regression exhibited high reliability, with an accuracy of 0.994–0.997 using gray and blur filters. KNN, although originally less successful, showed significant enhancement when integrated with blur filtering, attaining an accuracy of 0.973. Conversely, edge detection was found to be detrimental to the performance of all tested models.
P Penerapan Metode MAUT dengan Pembobotan Entropy Untuk sistem Pendukung Keputusan Pemberian Reward Tahunan Pada Karyawan PT. Sumber Jadi Kencana Motor Devi, Devi Purnamasari; Murdani; Fitri Aisyah Ritonga
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 04 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i04.1590

Abstract

PT. Sumber Jadi Kencana Motor merupakan sebuah perusahaan swasta yang berletak di sorum Yamaha SJKM, jalan kelambir V, tanjung Gusta, Medan Helvetia, Kota Medan., sebagai perusahaan yang bergerak dibidang otomotif dan jasa layanan kendaraan sangat memahami kinerja karyawan dalam menunjang kualitas layanan dan kepuasan pelanggan. Penulis meneliti perusahaan tersebut di karenakan perusahaan tersebut memiliki permasalahan dalam pemberian reward tahunan yang setiap tahunnya diberikan untuk karyawan perusahaan terkhusus pada bagian sales. Sehingga peneliti membuat sebuah keputusan yang dapat membantu pihak manajemen dalam proses pemberian reward. Pada sistem pendukung keputusan yang dilakukan menggunakan metode MAUT dengan pembobotan Entopy, yang dimana pembobtan entropy digunakan untuk menentukan nilai bobot kriteria dar setiap kriteria yang sudah ditentukan, sedangkan metode MAUT digunakan untuk menghasilkan hasil perangkingan yang berdasarkan dari alternatif dan kriteria yang sudah ditentukan. Maka hasil yang diperoleh dari sistem pendukung keputusan yang sudah dibangun dengan menggunakan metode MAUT dengan pembobotan Entropy ini, sangat bertujuan untuk mempermudah PT. Sumber Jadi Kencana Motor dalam proses pemberian reward yang terbaik dan objektif, cepat, dan tepat. Sehingga menghasilkan sebuah keputusan hasil dengan nilai terbesar yaitu 0.9959 dari alternatif A3 atas nama Chandra Gunawan Rambe.

Page 19 of 20 | Total Record : 196

 16   17   18   19   20 

Filter by Year

2020 2025


Reset
Filter By Issues
All Issue Vol. 7 No. 04 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 7 No. 02 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 7 No. 01 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 6 No. 03 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 6 No. 02 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 6 No. 01 (2024): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 5 No. 02 (2023): Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 5 No. 01 (2023): Jatilima : Jurnal Multimedia Dan Teknologi Informasi Vol. 4 No. 02 (2022): Jatilima Vol. 4 No. 01 (2022): Jatilima Vol. 3 No. 02 (2021): Jatilima Vol. 3 No. 01 (2021): Jatilima Vol. 2 No. 2 (2020): Jatilima Vol. 2 No. 1 (2020): Jatilima More Issue