Article Per Year (5 Year)
p-Index From 2020 - 2025
1.235
P-Index
This Author published in this journals
All Journal International Journal of Community Service Learning Bulletin of Computer Science Research Journal of Informatics Management and Information Technology KLIK: Kajian Ilmiah Informatika dan Komputer International Journal of Informatics and Data Science
Desyanti
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Environmental Science Law, Crime, Criminology & Criminal Justice Social Sciences

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

Found 7 Documents
Search

 1 
Pemanfaatan Algoritma C4.5 untuk Mendukung Pemilihan Konsentrasi Studi yang Tepat di Teknik Informatika Desyanti; Rudi Faisal
Bulletin of Computer Science Research Vol. 4 No. 6 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i6.345

Abstract

Choosing the right study concentration in the Informatics Engineering Study Program is crucial in supporting the success of the student's learning process and career. Currently, when choosing a contrast for the information engineering study program at Campus This research uses the C4.5 algorithm to build a decision tree to help students determine study concentration based on variables such as gender, high school major, course grades, and interests and talents. This method begins with the Knowledge Discovery in Databases (KDD) process which includes data selection, data cleaning, and transformation using a Likert scale. Data from 74 fifth semester students were analyzed to produce relevant decision rules. The implementation results show that the C4.5 algorithm is able to provide high accuracy in determining the appropriate study concentration. This system is expected to be a decision support tool for students and educational institutions in the majoring process
Edukasi 3R dalam Penanganan Sampah Menuju Sekolah Adiwiyata Sari, Febrina; Abdillah, Nuryasin; Desyanti
International Journal of Community Service Learning Vol. 8 No. 4 (2024): November
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/ijcsl.v8i4.85157

Abstract

Permasalahan utama adalah penumpukan sampah yang semakin meningkat di lingkungan sekolah.  Sampah organik dan anorganik tidak terkelola dengan baik, siswa masih membuang sampah organik dan anorganik menjadi satu di tempat sampah yang sama sehingga menyebabkan penumpukan sampah. Tujuan dari kegiatan ini adalah Tujuan penelitian ini untuk menganalisis edukasi 3R dalam penanganan sampah menuju sekolah adiwiyata SD. Rangkaian kegiatan untuk menyelesaikan permasalahan mitra dilaksanakan dalam beberapa tahapan mulai dari sosialisai, pelatihan dan penerapan iptek. Hasil penelitian yaitu kegitan ini menyediakan sarana prasarana pengelolaan sampah yang mendukung, seperti tempat sampah terpisah untuk sampah organik dan anorganik, dengan adanya kegiatan ini maka siswa dapat memilah sampah dan membuang sampah sesuai dengan jenisnya, mengajarkan siswa untuk meningkatkan kebersihan lingkungan. Dampak dari kegiatan ini adalah berkurangnya sampah yang berserakan di lingkungan sekolah karena sudah ada tempat sampah yang sesuai dengan jenis sampah, meningkatnya kesadaran siswa untuk menjaga lingkungan sekolah agar tetap bersih dan bebas dari sampah. Implikasi penelitian ini yaitu mitra telah memiliki pengetahuan dan keterampilan dalam mengelolah sampah yang ada di sekolah dengan metode 3R, sehingga sampah memiliki nilai juga.
Kombinasi Metode Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) dan Pembobotan Rank Order Centroid (ROC) dalam Pemilihan Tablet PC Terbaik Ryan Prayoga; Adinda Tria Suci; Titus Kristanto; Samsul Lutfi; Desyanti; Yonky Pernando
Journal of Informatics Management and Information Technology Vol. 3 No. 2 (2023): April 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jimat.v3i2.256

Abstract

Tablet PC which is one part of technological developments in the field of communication that aims to meet the needs of users where these needs are not found on smartphones or laptops, is an option that can be an alternative communication tool that can meet needs involving a smartphone. such as designing, playing games, and working. related to the many models of tablet PCs in the world of communication causes the selection of the best tablet PC to be a problem for the users themselves. One of them is if the user chooses the wrong type of tablet PC according to their needs, the tablet PC does not make it easier, instead it hinders the activities of the user himself. therefore data from the types of tablet PCs are collected from 5 criteria and 7 alternatives where the criteria have been determined including screen size, memory capacity, memory type, hard disk capacity and price. From these criteria, the use of ROC can be used to giving weight to each criterion which is then determined using the MOORA method included in the decision that can give the maximum and accurate final preference value, so this study determines the best tablet pc choice option is alternative A1 brand apple ipad air with a final value of 0.054 as the best alternative.
Clustering of YouTube Viewer Data Based on Preferences using Leiden Algorithm Erlin Windia Ambarsari; Aulia Paramita; Desyanti
International Journal of Informatics and Data Science Vol. 1 No. 2 (2024): June 2024
Publisher : ADA Research Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64366/ijids.v1i2.45

Abstract

This study aims to analyze YouTube viewer engagement patterns by applying the Leiden algorithm for clustering based on user interactions such as likes, dislikes, and subscription behaviors in correlation with video duration. Therefore, the method that we used begins with data cleaning to ensure completeness, followed by selecting relevant features and applying z-score normalization to equalize their contributions. A similarity graph is constructed using cosine similarity, representing instances as nodes and their relationships as edges. The Leiden algorithm is then applied to optimize modularity and extract clusters, with results integrated into the original dataset for analysis. Dimensionality reduction using PCA facilitates cluster visualization, while statistical summaries and distribution plots provide deeper insights into cluster characteristics. Subsequently, we obtained a dataset sourced from the YouTube content creator @ArmanVesona, which includes 237 instances with ten features: Shares, Comments Added, Dislikes, Likes, Subscribers Lost, Subscribers Gained, Views, Watch Time (hours), Impressions, and Click-Through Rate (%). The analysis reveals two distinct clusters: Cluster 0, characterized by lower engagement and stable audience, and Cluster 1, exhibiting higher engagement but higher subscriber churn. The findings highlight the effectiveness of the Leiden algorithm in detecting well-connected communities and provide insights into viewer behavior, aiding in the development of improved content strategies and targeted marketing approaches.
Penerapan VLAN pada VAP Menggunakan Mikrotik CAPsMAN untuk Manajemen Bandwidth Berbasis PCQ Satria, Devit; Desyanti
Journal of Informatics Management and Information Technology Vol. 5 No. 3 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jimat.v5i3.696

Abstract

This study uses the Network Development Life Cycle (NDLC) method to design and test a Mikrotik-based wireless network system in a fast-food restaurant environment. The system integrates CAPsMAN, Virtual Local Area Network (VLAN), Virtual Access Point (VAP), and Per Connection Queue (PCQ) technologies to create a centrally managed and efficient network. Two separate SSIDs are configured for internal Employee and external Consumer users, each allocated 7 Mbps and 13 Mbps of bandwidth out of a total of 20 Mbps. Test results show that the system is able to divide bandwidth fairly, assign IP addresses according to VLAN segments, and implement a time-based hotspot login for 1 hour. Connection success reached 100% without IP conflicts or traffic dominance. These results prove that the combination of CAPsMAN, VLAN, VAP, and PCQ is effective in dense user environments with temporary access needs.
Film Popularity Analysis through Combined K-Means Clustering and Gradient Boosted Trees Agi Candra Bramantia; Desyanti; Jeperson Hutahaean; Erlin Windia Ambarsari
International Journal of Informatics and Data Science Vol. 2 No. 2 (2025): June 2025
Publisher : ADA Research Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64366/ijids.v2i2.81

Abstract

The dynamic and competitive nature of the global film industry presents complex challenges in predicting film popularity, as success is shaped by the interplay of production investment, casting decisions, and audience preferences. This research addresses the limitations of previous studies that have focused primarily on direct relationships, such as budget versus box office returns, by introducing an integrated analytical framework that combines K-Means clustering and Gradient Boosted Trees (GBT) with explainable AI techniques. Utilizing the TMDB movie dataset and constructing features such as actor influence and studio power, the study segments films and predicts audience ratings while providing interpretable visualizations. The results reveal four distinct film clusters and demonstrate that actor influence and budget allocation are the most significant predictors of popularity. The proposed model achieves an R² score of 0.75 and a mean squared error of 0.35 in predicting audience ratings, while cluster analysis shows that Blockbuster films reach the highest average ratings (6.76), and Underperforming films the lowest (2.42). By integrating interpretable predictive modeling and interactive scenario tools, this research offers both theoretical advancement and practical value for industry stakeholders. However, the findings are limited by the available metadata and do not account for factors such as marketing or real-time audience trends, suggesting opportunities for future research to expand the analytical framework.
Combination of Multi-Attributive Ideal-Real Comparative Analysis and Rank Order Centroid in Supplier Performance Evaluation Arshad, Muhammad Waqas; Setiawansyah; Mesran; Desyanti
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 4 (2024): Februari 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i4.1677

Abstract

Supplier performance evaluation is a critical aspect of supply chain management that focuses on assessing and monitoring the performance of suppliers. Supplier performance evaluation not only provides benefits for the company, but also motivates suppliers to improve their quality standards and operational efficiency. This study aims to evaluate supplier performance based on existing assessment data by applying the ROC method to determine the weight of the criteria used, then the MAIRCA method will evaluate supplier performance so that it will produce a rating of supplier performance evaluation which will be a decision recommendation for companies in assessing the performance of existing suppliers. The combination of ROC and MAIRCA weighting methods forms a powerful approach in addressing the complexity and challenges of multi-criteria decision making. ROC with its focus on relative ranking criteria, whereas MAIRCA which considers the difference between ideal and real conditions, presents complementary perspectives. By combining the two, decision makers can generate a more contextual and informational weight of criteria. The ranking result graph in figure 4 shows the best supplier performance obtained on behalf of Supplier C with a final value of 0.052391944 ranked 1, then on behalf of Supplier F with a final value of 0.050077222 ranked 2, and on behalf of Supplier G with a final value of 0.049074028 ranked 3.
Co-Authors Adinda Tria Suci Agi Candra Bramantia Arshad, Muhammad Waqas Aulia Paramita Erlin Windia Ambarsari Jeperson Hutahaean Mesran, Mesran Nuryasin Abdillah Pernando, Yonky Rudi Faisal Ryan Prayoga Samsul Lutfi Sari, Febrina Satria, Devit Setiawansyah Setiawansyah Titus Kristanto