Jurnal Ilmu Komputer dan Sistem Informasi

Sistem Pendukung Keputusan Penentuan Instruktur Terbaik Dengan Kombinasi Metode GADA dan GRA Pada Tecnho Garage

Dedi Leman — 2025-05-31

Instructors play a vital role in the success of training programs at non-formal education institutions such as Techno Garage. The selection of the best instructor has traditionally been conducted manually, making it prone to subjectivity and inconsistency in decision-making. To address this issue, this study designs a web-based decision support system that combines two multi-criteria decision-making methods: Grey Absolute Decision Analysis (GADA) and Grey Relational Analysis (GRA). The GADA method is used to assign relative weights to each criterion and prioritize alternatives based on absolute values, while the GRA method is applied to handle uncertainty and complex relationships among criteria. The evaluation criteria include attendance, length of service, participant feedback, and contributions to material development. The results demonstrate that the combination of GADA and GRA methods provides more objective and accurate recommendations in selecting the best instructor. This system enhances the efficiency, transparency, and accountability of the instructor selection process.

Perancangan Media Pelatihan Digital Marketing Untuk Peningkatan UMKM Berbasis Website

Muhammad Alwi Hafizh — 2025-05-31

The internet is widely used in today's digital era. With the internet, people around the world communicate in a virtual platform called Social Media such as Facebook, Instagram, Twitter and TikTok. With Social Media, a business actor (MSME) can market their products locally, nationally and even internationally so that they can increase sales. Marketing via social media is also called digital marketing. There are still many MSMEs in Medan City who do not understand digital marketing techniques, so it is necessary to provide training to Medan City MSMEs. However, the large costs of offline training hinder the implementation of the training. For this reason, a web-based training media was developed so that training is carried out online so that training costs can be efficient. Development of digital marketing training media using Codeigniter 3.0 and is only intended for Medan city MSMEs.

ARphabet: Pembelajaran Abjad Inovatif Berbasis Augmented Reality untuk Anak Usia Dini

RM Chairil Andri — 2025-05-31

Letter recognition is a fundamental aspect of early childhood literacy development. Unfortunately, conventional media such as printed books and flashcards often lack appeal due to their limited ability to deliver simultaneous visual and auditory stimuli. This study aims to develop and evaluate an interactive Augmented Reality (AR)-based learning application called ARphabet, designed to assist young children in recognizing letters through 3D visualizations, supporting objects, and pronunciation audio. The application was developed using the Multimedia Development Life Cycle (MDLC), which includes the stages of concept, design, material collection, assembly, testing, and distribution. Evaluation was conducted through two approaches: expert validation using a questionnaire instrument with indicators including ease of use, effectiveness of content delivery, child appropriateness, and interactivity; and user testing using a quantitative approach through pre-tests and post-tests involving 21 kindergarten students. The expert validation results indicated a high feasibility score, with an average of 92.5%. Meanwhile, user testing showed that 90.5% of the children demonstrated improved letter recognition after using the application. These findings suggest that the use of AR technology can offer an innovative and effective solution to support early childhood literacy learning. The application also holds potential for further development, including syllable introduction, vocabulary building, or other age-appropriate educational content.

Analisis klasifikasi Algoritma K-Nearest Neighboar (K-NN) pada struktur Daerah di Kota Medan

Safa Nadia Bakri — 2025-05-30

This research aims to analyze the application of the K-Nearest Neighbor (KNN) algorithm in classifying regional structures in Medan City. Medan, one of the largest cities in Indonesia, has a variety of characteristics of regional structure that requires an appropriate analysis approach for spatial management and spatial planning. The KNN algorithm was chosen because of its ability to categorize data based on its proximity to other data points, which is very suitable for the needs of spatial planning and management. other data points, which is very suitable for the needs of regional classification analysis. In this research, the data used includes various attributes of the regional structure such as structure attributes such as population density, land use, and infrastructure in each sub-district. infrastructure in each sub-district in Medan City. In this research, the method used is statistical data processing statistical data processing to group areas with similar characteristics, using the KNN algorithm as a classification method. The classification process process involves selecting the right parameters, calculating the distance between data points, and selecting the optimal number of nearest neighbors. data points, as well as selecting the optimal number of nearest neighbors. The expected results The expected results of this analysis will provide a clear picture of the distribution pattern of the distribution pattern of the regional structure in Medan City, as well as assisting in the planning and development of a more efficient and directed city. The accuracy of the KNN model in classifying the regions will also be compared with other algorithms to assess its effectiveness and reliability in the context of this study.

Penerapan Sistem Pendukung Keputusan Berbasis Metode SAW Untuk Pemilihan Ketua Himpunan Mahasiswa Fakultas Teknik dan Informatika

Vanya Intan Amabel Adelia — 2025-05-31

An organization's direction and success are greatly influenced by the process of choosing its leaders. However, due to the subjective nature of evaluations, this process often struggles to identify the best candidate. This study aims to elect the Head of the Student Association at the Faculty of Engineering and Informatics using the Simple Additive Weighting (SAW) method as a decision support tool. The SAW method was chosen for its ability to evaluate and rank candidates based on several predetermined criteria. Utilizing a case study and a quantitative approach, data was collected through surveys, interviews, and direct observations. The criteria considered include semester, GPA, organizational experience, recommendations, and previous roles, with each criterion assigned a preference weight. The data was then processed through normalization and weighted summation, revealing that candidate number one achieved the highest score of 0.9895. The study concludes that the SAW method is an effective tool for facilitating objective and data-driven decision-making in the selection of organizational leaders.

Keywords: Leadership Selection, Decision Support System, Simple Additive Weighting (SAW)

Optimalisasi Random Forest untuk Sentimen Bahasa Indonesia dengan GridSearch dan SMOTE

Ahmad Fauzi — 2025-05-31

This research focuses on optimizing the Random Forest algorithm for sentiment analysis of social media x in Indonesian using TextBlob as a labeling tool, followed by the SMOTE data balancing technique and hyperparameter optimization with GridSearch. The data used was taken from 611 tweets with the keyword ukt (single tuition). Sentiment labeling using TextBlob produces 438 negative sentiments and 173 positive sentiments. The SMOTE method is used to balance the data by first dividing the data into 75% training data and 25% test data. Data vectorization using tf-idf. The Random Forest algorithm model was evaluated with an initial accuracy using split data of 73%, and cross validation evaluation with 10 k-folds produced an accuracy value of 75%. Optimization carried out with GridSearch hyperparameters succeeded in increasing the accuracy value to 74%, while cross validation evaluation using 10 k-fold accuracy was 89%. In this research, the SMOTE method was effective in balancing unbalanced data, and gridsearch hyperparameter optimization succeeded in increasing the accuracy value of the Random Forest algorithm in classifying social media sentiment x in Indonesian with automatic texblob labeling.