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
Implementasi Aplikasi Berbasis Mobile menggunakan Framework React Native dan Algoritma C4.5 untuk Rekomendasi Kelayakan Penerima Bantuan Yatim Impian Indonesia Mochammad Alvian Kosim; Setiawan Restu Aji; Muhammad Darwis
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.v7i4.6783

Abstract

One of the programs of Yatim Impian Indonesia, a foundation that focuses on social and education, is sharing carts for MSMEs (Gedor UMKM). Cart beneficiaries are selected based on certain qualifications so that they are considered eligible. However, in its implementation, there are problems in determining the eligibility of beneficiaries quickly. One of them is that the selection criteria have not been structured. To overcome the difficulties in determining the eligibility of beneficiaries quickly, a classification model is needed. This research aims to create a cross-platform mobile application that has the function of classifying the eligibility of beneficiaries by utilizing the C4.5 decision tree algorithm. This algorithm can provide recommendations to the foundation regarding whether the beneficiary is eligible to get a cart, based on the performance of the decision tree in the C4.5 algorithm. Furthermore, the classification model obtained from the decision tree is implemented in a mobile application to meet the needs of foundation administrators who are on duty in the field in conducting surveys. Using K-Fold Cross Validation Testing, the results of the C4.5 algorithm classification model show 81% accuracy in determining the eligibility of beneficiaries, and the results of the mobile application built with the React Native Framework which have been tested with Black Box testing show that all functional parts of the mobile application have run well.
Perbandingan Prediksi Obat Berdasarkan Pemakaian Menggunakan Algoritma Single Moving Average dan Support Vector Regression Said Nurfan Hidayad Tillah; Alwis Nazir; Iwan Iskandar; Elvia Budianita; Iis Afrianty
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.v7i4.6859

Abstract

To ensure the availability and quality of drugs, Public Health Centers (PHC) must pay attention to the planning and procurement process. The problem that often arises is the increase in drug stock due to the stable use of drugs each month, resulting in excess and expired drugs that are not used. In addition, it is necessary to avoid inappropriate drug demand, which affects stock availability. Drug usage prediction is done with several methods such as the Single Moving Average (SMA) algorithm in the data mining method and the Support Vector Regression (SVR) algorithm in the machine learning method. This algorithm was chosen because the drug data of Diazepam 5 mg and Mefenamic Acid 500 mg is sustainable from January 2020 to June 2023 (42 months). Implementation using the Phyton programming language. Testing using the Mean Absolute Percentage Error (MAPE) method, this study aims to measure the accuracy of predictions in each algorithm. In research with Diazepam 5 mg and Mefenamic Acid 500 mg drugs, with a division of 80% in training data and 20% in test data. With a calculation of 3 periods, the SMA algorithm produces MAPE values of 4.10% and 4.29%, in the "very good" range. The SVR algorithm, which uses an RBF kernel with a complexity parameter of 1.0 and an epsilon parameter of 0.1, produces MAPE results of 7.35% and 9.52%, in the "Very Good" range. Thus, the SMA algorithm predicts better than the SVR algorithm.
Penerapan Metode Fuzzy Tsukomoto untuk Mengukur Tingkat Kelayakan Produk Desyanti Desyanti; Denok Wulandari; Dewi Anjani
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.v7i4.6879

Abstract

Micro, Small and Medium Enterprises are one of the business fields that are in great demand by the public. MSMEs have their own advantages, namely that they can more easily carry out product development and can survive during an economic crisis. However, product feasibility is something that must be considered in MSME activities because it can provide benefits in terms of financial and social benefits. With a feasibility analysis, it is hoped that the risk of failure in marketing the product can be avoided. One of the MSMEs in the city of Dumai is X Cookies, a business that was built in 2019 and has many consumers who come to buy products from this home business, both in small and large quantities. To improve the quality of product suitability, you must evaluate the quality of the product provided to consumers whether it meets the expectations and desires of consumers or not. By using Tsukomoto's fuzzy logic, the level of suitability of X Cookies products can be determined. From the research carried out, the product feasibility level was not feasible = 0.39155 and feasible = 0.60845. So it can be said that the feasibility level for the X Cookies brownie product is at a feasible level.
Analisis Perbandingan Pembelajaran Online Dan Offline Terhadap Mahasiswa UIN SUSKA Riau Menggunakan Naive Bayes Nur Asiah; Idria Maita; Rice Novita; Eki Saputra; Arif Marsal
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.v7i4.6701

Abstract

Online lectures have become a common method used in education to deliver course materials to students. However, the exucution of Online lectures is not always smooth and often faces various challenges. One of the main issues is the limited internet access frequently experienced by students, particularly in regions where internet connectivity is limied, making it difficult for them to parcipate in lecturesnseamlessly. Addtionally, some students encounter difficulties in time management and self-motivation for independent learning. This research aims to analyst the conditions and issues that arise during the implementation of Online lectures and compare them with the traditional Offline lecture delivery at UIN SUSKA Riau. The Naïve Bayes algorithm is applied for the analysis, with a focus on Accuracy, Precision, Sensitivity, and specificity. The findings and analysis using this algorithm demonstrate a remarkable accuracy rate of 66,67%, precision rate of 70%, sensitivity rate of 77,78% and specificity rate of 50%. By looking at the results obtained, the Naïve Bayes method was successfully used in analyzing comparisons of Online and Offline learning for students of UIN SUSKA Riau.
Stress Detection Due to Lack of Rest Using Artificial Neural Network (ANN) Lukman Nurwahidin; Putu Harry Gunawan; Rifki Wijaya
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.v7i4.6642

Abstract

Currently, many people feel symptoms of stress due to lack of adequate rest. Which at this time the person will carry out activities that are very heavy both from tasks that are too heavy, work pressure that accumulates, and much more. People who experience stress symptoms sometimes don't know what causes stress. Through this research a learning machine will be made, using the Artificial Neural Network algorithm, will analyze heart rate data or BPM from 7 patient data per day, using a Fitbit smart watch will display several data such as falling asleep, waking up, REM (Rapid Eyes Movement) and, well, from the results of the data collected from the patients. Total data in this research are 36224. This research process will show the best accuracy results from several types of Artificial Neural Network algorithms. At the processing stage of the patient's heartbeat dataset, a comparison will be made between the types of Artificial Neural Network algorithms. The research will obtain the highest accuracy value of 81% from the results the Artificial Neural Network algorithm.
Clustering Analysis of Poverty Levels in North Sumatra Province Using the Application of Data Mining with the K-Means Algorithm Widyastuti Andriyani; Asyahri Hadi Nasyuha; Yohanni Syahra; Bagas Triaji
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.v7i4.6867

Abstract

North Sumatra, as one of the largest provinces in Indonesia, has serious challenges related to poverty that require serious attention North Sumatra, as one of the largest provinces in Indonesia, has serious challenges related to poverty that require serious attention and in-depth analysis. Thus, research on poverty levels in this province becomes very relevant and urgent. Therefore, a more in-depth analysis is needed regarding poverty levels in various regions within this province using data mining methods. The data mining approach is a way to gain understanding from large amounts of data. In the context of the problem of poverty levels, data mining has the potential to help reveal patterns that may be hidden in economic and social data. One algorithm that is often applied in clustering analysis is the K-Means algorithm. The K-Means algorithm is a clustering method that is widely used in data analysis and allows grouping data based on similar characteristics, so that it can be used to classify areas with similar levels of poverty. The results of this research show that data mining with the application of the K-Means algorithm can help produce more effective decisions in analyzing clustering of poverty levels in North Sumatra Province involving the use of data over a ten-year period, namely from 2013 to 2022, which records the number of poor people based on District and city. 3 groups were produced, namely 3 levels of poverty, including relatively stable, very vulnerable and vulnerable. Data from 33 districts or cities in North Sumatra resulted in a poverty level clustering of 1 city that was very vulnerable, 4 cities that were vulnerable and 27 cities that were relatively stable.
Sentiment Analysis Classification of ChatGPT on Twitter Big Data in Indonesia Using Fast R-CNN Sio Jurnalis Pipin; Frans Mikael Sinaga; Sunaryo Winardi; Muhammad Noor Hakim
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.v7i4.6816

Abstract

The advent of OpenAI's ChatGPT, a large language model (LLM) proficient in various fields including artificial intelligence (AI) and natural language processing (NLP), has ignited a plethora of opinions and discussions, especially on social media platforms like Twitter in Indonesia. This research seeks to delve into the intricate dynamics of these discussions, aiming to map both the commendations and criticisms surrounding ChatGPT's technological advancements and potential negative impacts. Utilizing deep learning-based sentiment analysis techniques, the study employs Convolutional Neural Network (CNN) and Fast Region-based Convolutional Network (Fast R-CNN) to analyze a dataset consisting of 7,604 tweets categorized into "Positive", "Negative", and "Neutral" sentiments. The objective is to provide a comprehensive understanding of the societal perceptions towards this artificial intelligence technology in the Indonesian context. The methodology encompasses several stages including data collection from Twitter, data cleaning, and pre-processing, followed by the application of CNN and Fast R-CNN models for sentiment analysis. The findings indicate a superior performance of the Fast R-CNN model, achieving an accuracy rate of 94.5%, compared to the CNN model with an accuracy rate of 86%. In conclusion, the research highlights the effectiveness of integrating Fast R-CNN in sentiment analysis to extract deeper insights from Twitter data in Indonesia. This study not only contributes to the scientific literature in the fields of sentiment analysis and natural language processing but also aids in formulating informed strategies to navigate the challenges and opportunities presented by artificial intelligence technology in the Indonesian landscape. Future research avenues should focus on optimizing this sentiment analysis model and exploring other potential applications of this technology in the dynamically evolving digital landscape in Indonesia.
Analisis Sentimen Terhadap Penggunaan Aplikasi Astro Menggunakan Algoritma Naïve Bayes Stevan Amadeo Prasetyo; Wahyu Tisno Atmojo
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.v7i4.6750

Abstract

Astro is a quick commerce application that focuses on providing fast groceries delivery services within less than an hour. It was established in 2021 under PT Astro Technologies Indonesia. Quick commerce applications are relatively new in Indonesia, and customer sentiments play a crucial role in determining the acceptance of this category within the society. Through reviews available on Google Play Store, we can gauge whether the majority of the populace holds a positive or negative sentiment towards it. The Astro app has been downloaded by over one million users, with a rating of 4.6 and more than 11.2 thousand reviews on Google Play Store. A total of 1,820 reviews were successfully obtained, and after preprocessing and data cleaning, 1,646 reviews remained. Subsequently, the data was labeled using the Naïve Bayes algorithm, categorizing sentiments into positive and negative. The results showed 1,213 reviews, or 74%, expressed a positive sentiment, while 433 reviews, or 26%, conveyed a negative sentiment. Using the confusion matrix, the classification performance achieved an accuracy of 63%, with a class recall of 61.58% for True Positive (TP) and 69.97% for True Negative (TN). The class precision for True Positive (TP) was 83.93%, and for True Negative (TN) was 38.36%. Based on the analysis, it can be concluded that the majority of Astro app users have a positive sentiment. However, a notable portion holds a negative sentiment, providing valuable insights to address concerns raised by users with negative sentiments.
Klasterisasi Jawaban Uraian Mahasiswa Menggunakan TF-IDF dan K-Means untuk Membantu Koreksi Ujian Irsyad Arif Mashudi; Sofyan Noor Arief; Deasy Sandhya E.I.; Triana Fatmawati; Mamluatul Hani’ah; Irfan Thalib Alfarid
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.v7i4.6688

Abstract

One way to ensure students understand a topic is by giving them essay questions. Essay questions provide a more accurate evaluation compared to other types of questions. However, this raises new problems where lecturers often have not found an effective way to assess answers to essay questions. The large number of students makes the assessment process take a long time. However, in reality, there are many similarities in the answers between students. These similar answers can be grouped and given the same grade. Unfortunately, if done manually, this grouping takes a very long time. Clustering is one way that can be used to determine variations in student answers as a whole. TF-IDF and K-Means are the clustering algorithms that are considered the strongest and most popular. By using TF-IDF and K-Means to help lecturers group students' descriptive answers, it turns out to be quite effective because with a percentage of conformity to the grouping results of 65%, lecturers can group descriptive answers in a much faster time than manually grouping descriptive answers.
Analisis Sentimen Masyarakat Terhadap Perilaku Korupsi Pejabat Pemerintah Berdasarkan Tweet Menggunakan Naive Bayes Classifier Abdul Syakir; Firman Noor Hasan
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.v7i4.6648

Abstract

The corrupt behavior of government officials is a problem that worries the public and threatens the integrity of the government system. In today's digital era, social media is an important means for the public to voice their opinions and sentiments on social issues, including the corruption of government officials. This study aims to analyze public sentiment toward the corrupt behavior of government officials based on tweet data on social media using the Naïve Bayes Classifier method. Tweet data is taken from social media Twitter related to corruption cases involving government officials within a certain period. The data is then processed to remove irrelevant elements and extract the sentiments contained in the tweets The Naïve Bayes Classifier method is applied to classify these tweets of positive, negative, or neutral sentiment toward corrupt behavior from government officials. The results of this study conclude that the public is very angry, disappointed, and has a low level of trust in corrupt behavior committed by government officials. Proven by the most dominant sentiment category is negative sentiment with 224 data and 95 data fall into the positive sentiment category.