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 54 Documents
Search results for , issue "Vol 7, No 4 (2023): Oktober 2023" : 54 Documents clear
Perbandingan Algoritma K-Means Dan K-Medoids Untuk Pemetaan Hasil Produksi Buah-Buahan Eka Prasetyaningrum; Puji Susanti
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6477

Abstract

In general, in 2019-2020 fruit production in Kotawaringin Timur district has decreased. Based on the data on fruit production, the amount of fruit production decreased, resulting in scarce fruit stocks and expensive fruit prices. Based on these problems, fruit production will be grouped according to the type of production in East Kotawaringin district using data mining techniques with clustering techniques using the K-Means algorithm and K-Medoids algorithm in order to optimize and increase fruit production. The results of grouping fruit production will be divided into 3 clusters, namely the highest cluster, the medium cluster, and the lowest cluster, making it easier for the Food and Agriculture Security Service in East Kotawaringin district to calculate and increase agricultural yields, especially in the horticulture sector. Based on the test results using data in 2019-2022, totaling 29 data in the Rapidminer application version 9.9 by comparing the DBI (Davies Bouldin Index) values of the two algorithms with so that the conclusion in determining the best value for the number of clusters (K) is that the fourth experiment shows 0.296 DBI (Davies Bouldin Index) values with six clusters. If the DBI value is smaller or closer to 0, then the cluster results obtained are more optimal. The results obtained in the K-Means algorithm get a smaller DBI (Davies Bouldin Index) value with a value of 0.296 while the K-Medoids algorithm results with a DBI (Davies Bouldin Index) value of 0.507. The best algorithm for clustering fruit production in Kotawaringin Timur district is the K-Means algorithm based on the DBI values obtained.
Analisis Perbandingan Teorema Bayes dan Certainty factor dalam Mendiagnosa Von Hippel-Lindau Disease Kusno Harianto; Azahari Azahari
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6778

Abstract

This research aims to compare the effectiveness of two diagnostic methods in identifying Von Hippel-Lindau (VHL) disease, namely the Bayes' Theorem and Certainty Factor. VHL is a rare disease that affects organs such as the brain, eyes, and kidneys. Health is a precious asset for humans, and often the assistance of specialized doctors is required to diagnose complex conditions like VHL. In the era of modern technology, the fusion of medical science with artificial intelligence has provided a fresh impetus in the development of expert systems to support faster and more accurate medical diagnoses. The Bayes' Theorem method is a statistical technique used to calculate the level of certainty in medical data. It helps measure the probability of whether someone has VHL or not. On the other hand, Certainty Factor is another method that gauges the level of confidence in diagnosing a disease using specific metrics, such as how certain symptoms are related to the disease. This research will conduct experiments on both methods using existing medical data and VHL cases. We will compare the accuracy, efficiency, and speed of both methods in diagnosing VHL. The results of this study are expected to provide valuable insights into which method is better suited to support VHL diagnosis. The implementation of expert systems in the field of medicine is crucial as it can assist doctors in making better decisions. The findings of this research can contribute to the development of more advanced and accurate medical expert systems, which, in turn, will enhance the care and prognosis of patients with VHL and other diseases. Thus, this research has the potential for significant impact in the fields of health and computer science. The results of the study indicate two methods in diagnosing Von Hippel-Lindau disease: "Certainty Factor" with a certainty level of 97.44%, and "Bayes' Theorem" with a certainty level of 41.22%. This provides insights into the relative effectiveness of both methods in diagnosing the disease, with "Certainty Factor" appearing to be more reliable.
Sistem Pendukung Keputusan Penerapan Metode EDAS Dalam Menyeleksi Konten Youtube Terbaik Untuk Anak Usia Dini Salmon Salmon; Pitrasacha Adytia; Muhammad Fahmi
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6747

Abstract

Youtube is an online video platform that has become one of the most popular and widely used websites in the world. YouTube's main goal is to provide facilities for content creators to upload the videos they create, interact with their audiences and provide users with a better and innovative video viewing experience, with features such as video browsing tailored to the user's interests and improved video quality. YouTube content is a term that refers to videos or other material uploaded to the YouTube platform, which is currently one of the largest websites in the world for sharing videos. In selecting Youtube content for early childhood, there are several criteria, namely: entertaining, not pornographic elements, increasing insight, not being violent, being creative. The results showed that the EDAS (Evaluation Based on Distance From Average Solution) method can provide an objective and accurate assessment by considering various relevant criteria. So as to produce YouTube content Omar and Hana ranked first (A2) with a score obtained 0.084 is YouTube content that is appropriate for children at an early age.
Analisis Sentimen Opini Pengguna Twitter Terhadap Tragedi Kanjuruhan Malang dengan Metode Support Vector Machine Fahri Putra Herlambang; Donny Avianto
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6332

Abstract

The Kanjuruhan tragedy on October 1, 2022, strongly impacted Indonesian football stadium safety. At the Kanjuruhan Stadium, a Persebaya vs. Arema FC match resulted in the deaths of 135 supporters. Due to the significant number of fatalities, there is ongoing debate regarding the responsible parties for the tragedy. Since there are expected to be 18.45 million active users in Indonesia by 2022, Twitter research helps determine popular attitudes. Support Vector Machine is used in this work to evaluate tweets and identify whether they include positive or negative emotions. The categorization outcomes may influence how the public views those responsible for the tragedy. On October 6, 2022, specific Twitter data on tear gas riots, oppressive government, rivalry between supporters, and violence against authorities were taken into account. The sentiment classes are negative, neutral, and positive. The study attained a 95.55% f1-score, 95.16% accuracy, 97.56% precision, and 95.16% recall.
Sistem Pakar Deteksi Penyakit Otitis dengan Perbandingan Metode Certainty Factor, Teorema Bayes, dan Dempster Shafer Abdul Karim; Shinta Esabella; Mhd Ali Hanafiah; Muhammad Bobbi Kurniawan Nasution; Andi Ernawati
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6595

Abstract

Otitis, especially otitis media, otitis externa, and otitis interna, is a common health issue in humans. Accurate identification and diagnosis are crucial for effective treatment. Expert systems have become an effective solution in this field as they can leverage medical knowledge to support decision-making processes. This research aims to develop an Expert System for Otitis Disease Detection using three different methods: Certainty Factor (CF), Bayes' Theorem, and Dempster-Shafer Method. The CF method is used to measure the level of confidence in decision-making, Bayes' Theorem utilizes probabilities to support diagnosis, and Dempster-Shafer matches previous cases with current symptoms to provide diagnostic recommendations. In this study, otitis symptom data were collected from previously diagnosed patients to train the expert system. The system was then tested with new cases to analyze the performance and accuracy of each method. The research results indicate that all three methods have the potential to detect otitis disease with varying levels of accuracy. In some situations, one method may outperform the others, suggesting that using a combination or integration of methods can enhance diagnostic accuracy. This research makes a significant contribution to the development of expert systems in the healthcare and medical services field. It is expected to assist doctors in the faster and more accurate diagnosis of otitis diseases. The calculation results show that the Certainty Factor method has the highest confidence level in diagnosing otitis media (86%), otitis externa (79%), and otitis interna (87%). While Dempster-Shafer has lower confidence levels in all cases, it still provides a significant contribution in certain situations. 
Prototipe Sistem Monitoring dan Kendali Suhu Box Kubikel 20 kV Berbasis Long Range (LoRa) Muhamad Ariandi; Yoza Risti Oktaria
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6796

Abstract

Electricity distribution often faces problems, one of which is interference with the 20 kV cubicle box caused by corona due to changes in temperature and condensation. This disturbance can cause arcing between the insulator and live parts. One solution is to use a heater and exhaust fan to maintain temperature and humidity. This study proposes a prototype to combine temperature and control heaters and exhaust fans automatically. Integrated sensors help monitor the temperature in the cubicle. Using a temperature sensor (DHT 22) shows high accuracy, and a current sensor (SCT 013) is suitable for exhaust fans and heaters. When the sensor is ready, the DHT 22 sensor will read the temperature in the room. If the reading temperature exceeds 40°C, then the exhaust fan will turn on to remove hot air in the cubicle box, whereas if the temperature is below 40°C the heater will turn on. If the detected temperature exceeds 43°C, and the exhaust fan does not turn on, a notification will appear on Blynk to immediately check the exhaust fan for errors. Meanwhile, if the temperature detects the cubicle box below the temperature of 37°C, a heater error notification will appear. The SCT 013 current sensor will detect the amount of current flowing in the exhaust fan and heater with the help of Esp32 as a microcontroller. This prototype utilizes LoRa technology for remote communication and sends notifications via the Blynk application. Tests show that this tool can help operators effectively monitor and control cubicle box temperature.
Weight-Based Hybrid Filtering in a Movie Recommendation System Based on Twitter with LSTM Classification Muhammad Nur Ilyas; Erwin Budi Setiawan
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6668

Abstract

With the era of digitalization, movie-watching has gained immense popularity, with platforms like Disney+ offering easy access to a variety of films. After watching, users frequently share their opinions on social media platforms such as Twitter, because of it is freedom of expression. With numerous movies available, users frequently encounter challenges in deciding what to watch. To address this, a recommendation system is proposed to streamline the decision-making process for users. Collaborative Filtering (CF), Content-Based Filtering (CBF), and Hybrid Filtering are common techniques used in recommendation systems. However, CF and CBF techniques face issues like cold start, sparse data, and overspecialization. To overcome these, this research constructs a Hybrid Filtering recommendation system, with a weight-based of CF-CBF coupled with Long Short-Term Memory (LSTM) classification. The classification uses various optimizers, including Adam, SGD, Nadam, RMSprop, and Adamax. Dataset is sourced from Kaggle website, which includes movie-related tweets linked to the Disney+ platform. The results indicate that Weight-Based Hybrid Filtering utilizing Adamax optimizer in LSTM classification yields superior performance metrics, by having 78% Precision, 79% Recall, 79% Accuracy, and 77% F1-Score value.
Penerapan Data Mining Untuk Klasifikasi Penerima Kredit Dengan Perbandingan Algoritma Naïve Bayes dan Algoritma C4.5 Dison Librado; Asyahri Hadi Nasyuha
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6907

Abstract

Credit is the process of borrowing money from customers to be paid over a certain period of time and with a payment agreement. In general, credit is provided by companies operating in the financial sector such as banks, cooperatives, business credit and finance. In the implementation process, providing credit to customers must be appropriate. In reality, the process of granting credit is still given to the wrong people. The problems faced must be resolved immediately and well, if the problems continue and giving credit not to the right customers will be very detrimental to the company. The settlement process can be done by looking at customer data that has previously received credit. Data mining is a technique that can be used to help solve these problems. In the process of resolving credit granting problems, data mining can be used to process previous credit customer data to obtain a pattern of which customers are eligible for credit. Classification is a method used in data mining to solve various kinds of problems. In this research, research will be carried out using the Naïve Bayes algorithm and the C4.5 algorithm. The method comparison process carried out in the research was carried out to obtain more definite results. This is based on the importance of giving credit to the right person so that there are no problems in the process of completing credit bill payments. Completion of data mining by applying the Naïve Bayes and C4.5 algorithms has been successfully carried out and classification can be carried out for decision making, both algorithms have the same decision making result, namely "Accepted". However, there are differences in the level of accuracy obtained. In the Naïve Bayes algorithm the accuracy level is 86.67%, while in the C4.5 algorithm the accuracy level is 100%.
Penerapan Deep Learning Dalam Pengenalan Endek Bali Menggunakan Convolutional Neural Network Theresia Hendrawati; Dewa Ayu Putri Wulandari; I Gde Swiyasa Surya Dharma; Ni Luh Wiwik Sri Rahayu Ginantra, M.Kom; Christina Purnama Yanti
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6721

Abstract

Endek Bali has been recognized as one of the Intellectual Property of Traditional Cultural Expressions, with registration number EBT 12.2020.0000085 on December 22, 2020. In the present era, many people find it difficult to distinguish between endek fabric and batik fabric because their patterns are quite similar. This research aims to help identify Bali's Endek fabric based on digital images. One of the approaches used is the Convolutional Neural Network method with ResNet50, which is a deep learning method used to recognize and classify objects in digital images. Evaluation result from testing the best model with new testing model using confession matrix get result of 90,69% accuracy, 90,69% recall, 90,60% precision and 90,68% f1-score. Thus, the model developed in this research demonstrates optimal performance in classifying images of Bali's Endek.
Meningkatkan Kemampuan Model dalam Memprediksi Penyakit Jantung dengan Algoritma NCL dan GridSearchCV Zulfan Ahmadi; Asrul Abdullah; Izhan Fakhruzi
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i3.6142

Abstract

Heart disease is the main cause of death in the world. To reduce this high mortality rate, accurate prediction capabilities are needed in warning people with heart disease to prevent and manage this condition. This study uses a machine learning model to predict heart disease. The purpose of this research is to improve the ability of a machine learning classification model, namely Logistic Regression (LR), in predicting heart disease. So that prediction errors that can harm patients can be significantly reduced. To achieve this goal, research is carried out using two important approaches, namely data preparation and model optimization. At the data preparation stage, data imbalance problems were found between people with heart disease and non-heart disease sufferers. To deal with this problem, the Neighborhood Cleaning Rule (NCL) algorithm is used to correct data imbalances. The use of NCL in the data preparation stage has a significant impact on improving the performance of the prediction model. Furthermore, at the model optimization stage, the GridSearchCV method is used to find the best hyperparameter combination in the Logistic Regression (LR) algorithm. By finding optimal hyperparameters, the performance of the prediction model can be improved. In addition, this study also implemented Weighted Logistic Regression which allows setting class weights, which also contributes to improving model performance. The results of testing the model using the evaluation metrics Accuracy, Recall, and Area Under Curve (AUC) show an increase in the ability of the model. The recall score increased from 0.10 to 0.93, and the AUC score increased from 0.83 to 0.98. This study used a dataset obtained from Kaggle from the Centers for Disease Control and Prevention (CDC). With better predictive ability in identifying heart disease, it is hoped that it can provide accurate early warning to individuals at risk, thereby significantly reducing mortality from heart disease.