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
Penerapan Metode VIKOR untuk Menentukan Kelayakan Perpustakaan Sekolah Diakreditasi Sukamto Sukamto; Aidil Fitriansyah; Avisha Delinda Jukris
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5489

Abstract

School libraries should be accredited with the aim of improving the quality of libraries. Pekanbaru City Library and Archives Service (DISPUSIP) in determining a school library that deserves to be accredited is still done manually. For this reason, a decision support system (DSS) is needed. This study uses the VIKOR method by steps of making a decision matrix, normalizing the criteria weight, determining the normalization matrix, determining the utility, determining the VIKOR index, and ranking. The alternative used is nine (9) junior high schools, both public and private. The criteria used refers to the school library accreditation instruments issued by the National Library that consist of six (6) criteria, namely collections, library facilities and infrastructure, library services, library staff, library administration and management, and reinforcement. The results obtained for the SMP library are Sek 4, Sek 7 and Sek 5 which are eligible for accreditation.
Implementasi Arsitektur EfficientNetV2 Untuk Klasifikasi Gambar Makanan Tradisional Indonesia Erin Eka Citra; Dhomas Hatta Fudholi; Chandra Kusuma Dewa
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5881

Abstract

Indonesia has many variations of traditional food and interesting tourist destinations. The large number of tourist destinations make people like traveling and try to enjoy their traditional food. However, when trying traditional foods, especially foods that are new to them, they must be more careful, because the various ingredients contained in them have an impact on health. This research will try to make an application that can recognize Indonesian traditional food. The hope is that it can provide complete information, so that it can be used to develop calorie counter applications in the future. This study aims to design a system that can classify Indonesian traditional food images to help recognize food names with a certain level of accuracy using the EfficientNetV2 architecture. EfficientNetV2 is a new family of deep learning that excels in training as well as parameter efficiency. Deep Learning is a method often used to classify complex images. The EfficientNetV2 used in this study consists of four different architectures namely EfficientNetV2_S_21k, EfficientNetV2_M_21k, EfficientNetV2_L_21k, and EfficientNetV2_XL_21k. The dataset used comes from three types of data source categories, namely from Google Images, direct image capture using a Smartphone camera, and a combination of both. Each dataset category consists of 18 classes with a total of 1,800 images from Google Images, 1,800 images from Smartphone cameras, and 3,600 images from a combination of Google Images and Smartphone cameras. The dataset is taken from three categories to compare the level of accuracy and get the best accuracy value. The results of this study indicate that EfficientNetV2 can classify images of Indonesian traditional food with the highest test accuracy value of 99.4% from the EfficientNetV2-L(21k) model and the results obtained do not occur overfitting.
Random Oversampling, Chi-Square, dan AdaBoost dalam Penanganan Ketidakseimbangan Kelas pada Klasifikasi C5.0 Tanti Tanti
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5862

Abstract

In data mining, there is a classification method. One of the problems often experienced in data mining classification is class imbalance. Class imbalance is a condition where the distribution of the dataset is uneven, meaning that it is divided into the majority class and the minority class with varying degrees of severity. The minority class is often misclassified because the majority class will be overclassified. This problem makes the classification process difficult and results in sub-optimal classification performance. Due to an imbalance, the classification will produce much higher accuracy for the majority class than for the minority class. This study aims to apply Random Oversampling, Chi-Square, and AdaBoost in overcoming class imbalances to optimize the performance of the C5.0 classification. In dealing with unbalanced datasets, performance appraisal needs to focus more on the positive class. So that the metric that is more suitable for assessing the classification results of unbalanced datasets is recall/sensitivity/TPR. The results showed that the application of Random Oversampling alone was able to improve the recall/sensitivity/TPR performance of standard C5.0. The application of Chi-Square alone has not been able to improve the performance of the C5.0 classification, but it has increased after the application of Random Oversampling. The combination of the three, namely Random Oversampling, Chi-Square, and AdaBoost able to increase the recall/sensitivity/TPR value of the standard C5.0.
Penerapan Algoritma Support Vector Regression dalam Memprediksi Produksi dan Produktivitas Kelapa Sawit Adyah Widiarni; Mustakim Mustakim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.6089

Abstract

Palm oil is a plantation crop that provides the highest economic value in Indonesia. Riau is currently the highest palm oil producing province in Indonesia with a state-run palm oil company, PTPN V. However, palm oil production is not always stable every month, whichexperiences ups and downs in the amount of production and productivity due to several factors including irregular rainfall, climate, soil fertility and most importantly fruit bunches that are not ready to harvest. So the data mining processing process is carried out by predicting the amount of production and productivity of oil palm applying the Support Vector Regression (SVR) algorithm with three kernels such as the Linear kernel, RBF kernel and Polynomial kernel. Experimental results on palm oil production and productivity show that the best kernel is the RBF kernel because the prediction results are close to the actual value. The accurate rate on palm oil production is 75.4% and palm oil productivity produces an accuracy value of 71%. It also produces an error value on palm oil production of 1.8%, for productivity of 2.1%. The results of the study can be used as an estimated picture in the company's future decision making.
Cluster Analysis using K-Means and K-Medoids Methods for Data Clustering of Amil Zakat Institutions Donor Hotmaida Lestari Siregar; Muhammad Zarlis; Syahril Efendi
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5315

Abstract

Cluster analysis is a multivariate analysis method whose purpose is to classify an object into a group based on certain characteristics. In cluster analysis, determining the number of initial clusters is very important so that the resulting clusters are also optimal. In this study, an analysis of the most optimal number of clusters for data classification will be carried out using the K-Means and K-Medoids methods. The data were analyzed using the RFM model and a comparative analysis was carried out based on the DBI value and cluster compactness which was assessed from the average silhouette score. The K-Means method produces the smallest DBI value of 0.485 and the highest average silhouette score value of 0.781 at k=6, while the K-Medoids method produces the smallest DBI value of 1.096 and the highest average silhouette score value of 0.517 at k=3. The results show that the best method for data clustering donations Amil Zakat Institutions is using the K-Means method with an optimal number of clusters of 6 clusters.
Data Clustering Mining Applying the K-Means Algorithm, Cervical Cancer Behavior Risk Ridha Maya Faza Lubis; Jen-Peng Huang; Pai-Chou Wang; Kiki Khoifin; Mula Sigiro; Joel Panjaitan
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.6088

Abstract

Nowadays, cancer is often heard as a topic of conversation for both men and women in Indonesia and even in the world, in addition to the symptoms that are not too significant and also the lack of public awareness to carry out periodic health checks, which has a negative impact on health. This lack of care is also caused by several factors, namely the lack of the community's economy, too busy with work (other matters) and even some people are not ready to know and accept the disease they are suffering from. Based on all the factors causing the reluctance of medical examinations, of course, it requires us to carry out examinations so that we can prevent and treat them early if they are diagnosed with certain diseases. There are several cancers with predominant sufferers and even only suffered by women, one of which is cervical cancer. In 2020 it is estimated that cases of cervical cancer will increase by 3.4% from 6.6% in 2018 to 9% and even cervical cancer will also become the third deadly disease in women after breast cancer and lung cancer. From this it can be seen that the percentage of deaths caused by cervical cancer is always increasing. Therefore, to reduce the high mortality rate, a clustering technique was carried out to group the data into their respective clusters based on the similarity of characteristics between one data and another. The algorithm used is K-Means with the rapid miner tester application. The final result obtained is that cluster 1 has more data and it is stated that out of 72 data on Cervical Cancer only 28 are declared as sufferers of Cervical Cancer and 44 other data are not.
Penerapan Algoritma Certainty Factor pada Sistem Pakar Diagnosis Penyakit Creutzfeldt-Jakob Disease Alex Wenda; Saludin Saludin; Sitti Nur Alam; Edy Winarno; Devin Mahendika
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5934

Abstract

Indonesia is a country that is active in the livestock sector, one of which is cattle farming. However, not many cows are affected by mad cow disease where this disease can be transmitted to humans by consuming the beef itself. This Gina cow disease, if it has been infected with humans, is called Creutzfeld-Jakob disease, where this disease can attack any part of the human body, namely the nervous tissue in the human brain so that it can destroy human brain cells and cause small holes in the brain automatically. gradually, the severity of this disease can claim a person's life if proper medical treatment is not carried out. This disease can cause death within one year after the symptoms are indicated as creutzfeld-jakob disease. To make it easier for an expert to diagnose a disease, a system can be used, namely an expert system with a certainty factor algorithm that determines the confidence value based on the percentage of the final Cfcombine value of the various types of symptoms that exist, so that the percentage value of the resulting confidence level is 89%.
Penerapan Metode MOOSRA dalam Rekomendasi Platform Investasi Emas Online Terbaik dengan Pembobotan ROC Hanifah Ekawati; Yunita Yunita
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.6063

Abstract

In the current era, technology is considered more practical in doing all kinds of things, for example, making investments that initially could only be done in person and were considered complicated, but now with technology, investments can be made online, making it more practical. Investments can be made by the younger generation, not only by their parents, the younger generation needs to learn about various things about investing with the aim of preparing for a brighter future. Investments that can be made by the younger generation can be in various forms, one of which is gold investment. Gold investment can be done by buying physical gold such as jewelry or gold bars, or by means of non-physical gold investment such as through the futures market, gold mutual funds, or online gold investment platforms. The online gold investment platform offers competitive gold prices and gold storage services in a secure warehouse to make it easier for investors to buy and sell gold online. However, because there are so many gold investment platforms, young gold investors are confused about determining the best online gold investment platform to use. The application of a decision support system is used in this study to solve problems in the recommendation of the best gold investment platform by applying the MOOSRA (Multi-Objective Optimization on the Basis of Simple Analysis) method and ROC (Rank Order Centroid) weighting. Then several criteria are used in the recommendations for the best gold investment platforms, namely Rating Reviews, Integrated E-commerce, Number of Payment Methods, Number of Partners and Minimum Purchases. By applying the MOOSRA and ROC methods, the best gold investment platform results with the highest preference value are obtained in alternative P2, namely BukaEmas with a value of 1151.88524.
Seleksi Penerima Bantuan Pangan Istimewa Menggunakan Metode Simple Multi Attribute Rating Technique Gellysa Urva; Welly Desriyati
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.6070

Abstract

BPI  is a routine program distributed by PT Amandika Permana once a year to workers with criteria determined by the company. The increasing number of workers makes it difficult for companies to select workers who are eligible for food assistance. In order for the distribution of food aid to be channeled on target, the company needs an analysis and quick calculations in the selection process. The implementation of the SMART (Simple Multi Attribute Rating Technique) method with a large number of criteria is able to solve existing problems. The implementation of the SMART method is determined by applying ten criteria in the form of employment status, income, number of dependents, home ownership status, residential land status, building area, movable assets, sources of drinking water, sources of house lighting and other assistance program cards. The final results of the study show that the use of the SMART method is able to assist users in determining BPI beneficiaries. The decision results are divided into three categories, where values 0.5 – 0.8 are recommended, 0.3 – 0.4 are considered, and values 0.1 – 0.2 are not recommended. Attachments to the selected data make it easy for users to make decisions efficiently and effectively. Based on the results obtained, the beneficiary who is most entitled to assistance also occupies the first position with a value of 0.75. Determining the appropriate weight value for each criterion affects the selection results to get the best results.
Penerapan Metode Saving Matrix Dalam Optimasi Rute Perjalanan Kunjungan Mitra Sekolah Untuk Peningkatan Strategi Marketing Kampus Nani Agustina; Martini Martini; Entin Sutinah
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i2.5955

Abstract

Bina Sarana Informatika University has a lot of campuses, one of which is in the Jatiwaringin area. In marketing activities, UBSI has a team called Markom. One of the success factors of UBSI's marketing is determined by visits to high schools around the UBSI Jatiwaringin campus, where this activity is carried out as a form of cooperation between UBSI and the school in carrying out promotions for campus events whose target is class XII students. In carrying out campus marketing activities, UBSI Jatiwaringin has 15 target schools around the campus. In carrying out the visit, Markom had problems in determining which schools to visit first, because in carrying out campus marketing activities, Markom only provided time with a duration of 08:00-12:00 by making visits starting from the UBSI Jatiwaringin campus and returned to the UBSI Jatiwaringin campus. So it is necessary to have an optimal route pattern to determine the minimum route in the school visit process. To overcome these problems need to apply a method. In this study the Saving Matrix method was used to determine the path and distance of visits to schools with optimal visiting times. The data obtained is in the form of school names, distances, and travel routes from UBSI Jatiwarigin to the schools to be visited. From the results of data processing, it was obtained that the visit time was 6 days with 6 routes with a travel time of 233 minutes which previously did not have rules for using routes but only based on estimates and urgency which sometimes took 8 days. The results of this study indicate that by using the Saving Matrix method the time needed is more optimal because the steps taken are appropriate in solving travel route problems and easy to implement.

Page 84 of 119 | Total Record : 1182