cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
mib.stmikbd@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
JURNAL MEDIA INFORMATIKA BUDIDARMA
ISSN : 26145278     EISSN : 25488368     DOI : http://dx.doi.org/10.30865/mib.v3i1.1060
Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer science)
Articles 1,182 Documents
Peramalan Jumlah Kedatangan Wisatawan Menggunakan Support Vector Regression Berbasis Sliding Window Fitriah, Ma’idatul; Permana, Inggih; Salisah, Febi Nur; Munzir, Medyantiwi Rahmawita; Megawati, Megawati
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7408

Abstract

As a developing city, Pekanbaru has the potential for attractive tourist attractions for tourists. The arrival of tourists has had a big positive impact on the economy of Pekanbaru City. The number of tourist arrivals can experience ups and downs every month, for this reason it is necessary to forecast the number of tourists in the future. This research aims to apply the Orange Data Mining application in predicting the number of tourist arrivals by comparing the kernels in the Support Vector Regression (SVR) method and applying Sliding Window size 3 to window size 13 to transform into time series data. As well as sharing data using the K-Fold Validation method with a value of K-10. Then the performance of the kernels used can be seen using the Test and Score widget which presents the results of Root Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), dan R-squared(R2). The results for forecasting the number of tourist arrivals to Pekanbaru City using the SVR method show that the RBF Kernel is the optimal choice compared to the Polinomial and Linear Kernels. The results of the Test and Score widget show that the RBF Kernel with window size 10 has lower MAE, MSE and RMSE values, namely 0.118, 0.022 and 0.147. Apart from that, the comparison of R2 in window size 10 for Kernel RBF shows better performance with a value of 0.519.
Pengembalian Data Yang Hilang Pada Dataset Dengan Menggunakan Algoritma K-Nearest Neighbor Imputation Data Mining Bangun, Budianto; Karim, Abdul Karim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.8014

Abstract

One of the things that is really hoped for when collecting data is to produce complete data. In research, incomplete data will affect the results obtained. because the process carried out in the research was not optimal. A dataset is a collection of information that is stored for a long time and becomes a large pile of data. Missing values in the dataset will be an important problem and must be handled in research. Therefore, data recovery is needed. Data mining is a process carried out in computer research. Where data mining will process data that has been collected first, either data collected by yourself (primary data) or data that has been collected in a dataset (secondary data). Recovery is the process of recovering data that is lost or cannot be found. The K-Nearest Neighbor Imputation algorithm is a system that uses a supervised learning algorithm and aims to discover new data patterns by connecting existing data patterns with new data. KNNI is an approach used to identify objects based on certain information, namely the closest distance to the object
Deteksi Serangan DDOS Pada Jaringan SDN dengan Metode Random Forest Ekawijana, Ardhian; Bakhrun, Akhmad; Kurniawan, M Teguh
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.6928

Abstract

Distributed Denial Service (DDoS) Attack is an attempt by an attacker to paralyze a network system by flooding it with requests. A busy system can cause a drop in performance and even crash. Software Defined Service (SDN) is a new paradigm in creating a network in a certain area. SDN, with all its advantages and flexibility in implementation, is attractive to implement, but still leaves major security problems, especially being vulnerable to DDoS attacks. This research will detect whether a particular request is DDoS or not. Random Forest is a method for developing Decision Trees to classify whether a request or data packet is an attack or not. Random Forest as a development method from the previous method covers the weakness of overfitting. The results of this research were 98% for accuracy values.
Data Mining Using Support Vector Machine Model for Baturraden Tourism Visitor Satisfaction Prediction Damayanti, Suci; Oktaviana, Luzi Dwi; Bratakusuma, Trias
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7346

Abstract

The tourism industry is a significant economic sector and a driver of local and national economic growth. Tourism not only contributes economically, but also plays an important role in introducing and preserving the cultural and natural wealth of an area. One of them is Baturraden tourism, a tourist destination located in Indonesia is experiencing a rapid increase in the number of tourist visits. Baturraden is a tourist destination located in the highlands at the foot of Mount Slamet, Indonesia, precisely in Banyumas Regency, Baturraden District. Tourists who visit every year are increasing but tour managers have not realized whether the tourists are satisfied or not so research is needed to measure the level of satisfaction of tourists so that the Baturraden tourism is better. To measure the level of satisfaction, an algorithm is needed, in this study the algorithm used is a support vector machine (SVM) to collect data that will be used as a dataset by taking reviews on google maps manually then the data is grouped into groups of satisfied and dissatisfied tourists, as many as 100 data are taken and processed. So that the final result obtained an accuracy value of 86.00%, and for reviews tend to be positive or satisfied tourists visiting the baturaden tourist area.
Sistem Rekomendasi Pemilihan Komponen Komputer Menggunakan Metode AHP dan Profile Matching Salmanarrizqie, Ageng; Vitianingsih, Anik Vega; Kristyawan, Yudi; Maukar, Anastasia Lidya; Marisa, Fitri
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7643

Abstract

Computers have become one of the technological tools that play a crucial role in enhancing society's productivity. Therefore, many desktop computer users assemble their own computers to achieve computer performance according to their preferences or needs. However, some people lack information about the variations, specifications, and capabilities of each computer component to be assembled. This research offers a recommendation system that is part of a decision support system (DSS) to assist users in providing recommendations for computer components that are being sought and needed based on brand, price, and specifications using the Analytic Hierarchy Process (AHP) and Profile Matching methods. Parameters are based on the processor, motherboard, graphics card (VGA), storage, RAM, power supply, and casing with priority categories based on specifications, price, and brand. Data weighting is done using the Analytic Hierarchy Process (AHP) method, while the Profile Matching method is used for ranking the weighting results. The research results show an accuracy rate of 60% using the Profile Matching method, while the AHP method achieves an accuracy rate of 57%.
Klasifikasi Penyakit Serangan Jantung Menggunakan Metode Machine Learning K-Nearest Neighbors (KNN) dan Support Vector Machine (SVM) Arif, Siti Novianti Nuraini; Siregar, Amril Mutoi; Faisal, Sutan; Juwita, Ayu Ratna
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7844

Abstract

Cardiovascular disease (CVD) is a general term for disorders related to the heart, coronary arteries, and blood vessels. These diseases are most commonly caused by blocked blood vessels, either due to fat buildup or internal bleeding. According to the WHO, each year, cardiovascular diseases account for 32% of all deaths, which translates to about 17.9 million people annually. The numerous factors causing CVD make it challenging for doctors to diagnose patients who are at low or higher risk of heart attacks. A machine learning model is needed for the early recognition of heart attack symptoms. Supervised learning models such as KNN and SVM were used in previous studies without feature selection, with datasets obtained from Kaggle. PCA was applied to reduce data dimensions to smaller variables. With the use of confusion matrix and ROC curve evaluations, the accuracy results of the previous KNN model improved from 83.6% to 90.16%. The SVM model also saw an accuracy increase from 85.7% to 86.88%. The use of PCA feature selection demonstrated an improvement in accuracy in the study. The KNN model, with a higher accuracy rate of 90.16%, is better for classifying individuals as normal or diagnosed with a heart attack.
Analisis Sentimen Pengguna Twitter Terhadap Bus Listrik Menggunakan Naïve Bayes Verawati, Ike; Jaelani, Syarif Nurwahid
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7030

Abstract

Twitter sentiment analysis is one method of identifying and classifying opinions into positive or negative sentiment in tweets. One of the topics that is being widely discussed on Twitter and has received various opinions for and against is electric buses. All of these opinions are still random and their sentiments have not been classified so sentiment classification needs to be carried out.Naïve Bayes can be used to classify sentiment and is easy to implement. The aim of this research is to classify whether sentiment regarding electric buses leads to positive sentiment or negative sentiment using Naïve Bayes and calculate the accuracy obtained. Several steps were taken, namely data collection, preprocessing, lexicon labeling, word weighting, naïve Bayes classification, and confusion matrix evaluation. The results of this stage from 4 trials of different data sharing ratios showed that the highest sentiment was positive sentiment which reached 77.31% with 22.69% negative sentiment at a data sharing ratio of 6:4 with the evaluation results using the confusion matrix obtaining an accuracy of 74.4%. After naïve Bayes was optimized with hyperparameter tuning, the accuracy increased to 78%. At a data sharing ratio of 9:1, the accuracy obtained after optimization shows a decrease to 71.5%, whereas initially Naïve Bayes obtained an accuracy of 75.6%, this shows that the data split ratio can influence the accuracy obtained by the classification model.
Multilabel Classification in Indonesian Translation of Religious Text using Word Centrality Term Weighting Dewantara, Muhammad Pascal; Lhaksmana, Kemas Muslim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7351

Abstract

This research focuses on enhancing the understanding of the Quran in the Indonesian translation dataset by employing a word centrality that feeds into a classifier model. The primary goal is to compare the hamming loss score from the TF-IDF and TW-IDF feature extraction methods in the Indonesia translation case study. The TF-IDF is commonly used in prior research. It has a higher hamming loss (which is worse in accuracy) than the TW-IDF incorporating centrality measurement more specifically in degree and closeness centrality. This research adds eigenvector centrality for a new compartment from the other methods. We used SVM, Random Forest (Bagging), and AdaBoost (Boosting) for the classifier model, with Mutual Information as the feature selection method. In evaluating the classifier, Hamming Loss is used given that the method is suitable for multilabel classification. Results indicate that the centrality measurement value for the term weighting method offers a significant improvement over regular TF-IDF. Each centrality method gives the best Hamming Loss score in each classifier model. Degree centrality gets 0.1275 in SVM, closeness centrality gets 0.1367 in AdaBoost, and eigenvector centrality gets 0.1204 in Random Forest. However, eigenvector centrality still can be a strong measurement method to lower the Hamming Loss score. Random Forest and AdaBoost give a significance better over SVM.
Implementasi Ensemble Deep Learning Untuk Analisis Sentimen Terhadap Genre Game Mobile Cahyadi, Marcelinus Fajar; Rochadiani, Theresia Herlina
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7832

Abstract

The rapid growth of the online gaming industry in Indonesia has prompted developers to address various challenges in creating successful mobile games. This study aims to evaluate the effectiveness of ensemble learning techniques, particularly soft voting, in enhancing sentiment analysis accuracy across 17 genres of mobile games. Additionally, it identifies the most effective deep learning model for sentiment classification. The research compares the performance of CNN-LSTM, BERT, and CNN-GRU models, as well as an ensemble of these models. Review data was collected from the Google Play Store, then labeled and cleaned to improve data quality, categorized into positive, neutral, and negative sentiments. Data preprocessing techniques included cleaning, case folding, tokenization, normalization, stopword removal, and stemming. Word embedding techniques used were Word2vec for CNN-LSTM and CNN-GRU models, and IndoBERT for BERT model. Ensemble learning combined predictions from these models, significantly improving classification accuracy. Results indicate IndoBERT achieved an accuracy of 89%, while CNN-GRU and CNN-LSTM showed accuracies around 84-85%. The ensemble approach using soft voting successfully increased overall accuracy to 90% by combining predictions from all three models. The study concludes that ensemble learning effectively combines individual model strengths to enhance sentiment classification accuracy. Furthermore, user preference visualization for game genres revealed high popularity for "Strategy", "Word", and "Trivia" genres, while "Sports" genres were less favored. This research is expected to contribute to game developers in determining which genres to develop to enhance success chances and user satisfaction.
Peningkatan Performa Model Machine Learning XGBoost Classifier melalui Teknik Oversampling dalam Prediksi Penyakit AIDS Wicaksono, Duta Firdaus; Basuki, Ruri Suko; Setiawan, Dicky
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 2 (2024): April 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i2.7501

Abstract

The data shows that HIV (Human Immunodeficiency Virus) has caused tens of millions of global deaths, with 630,000 people dying from HIV-related illnesses in 2022 and 1.3 million people newly infected with HIV. Without treatment, HIV can progress to AIDS (Acquired Immune Deficiency Syndrome), weakening the immune system and increasing the risk of infections and other diseases. Despite advancements in treatment, early detection of AIDS remains a priority. This research develops an AIDS prediction model using machine learning, which proves to be an effective solution in providing future health predictions. However, data imbalance issues challenge the model in predicting rare AIDS cases. To solve this problem, oversampling techniques are employed to balance the distribution of minority classes. This study explores oversampling techniques such as SMOTE, ADASYN, and Random Oversampling, combined with the XGBoost algorithm. The results show that the combination of Random Oversampling technique with the XGBoost Classifier yields the best performance with an accuracy of 94.44%, precision of 90.72%, recall of 98.74%, and an f1_score of 94.65%. This research is expected to provide valuable insights for healthcare practitioners and the public in efforts to control the spread of AIDS globally.