cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.json@gmail.com
Editorial Address
STMIK Budi Darma Jln. Sisingamangaraja No. 338 Telp 061-7875998
Location
Kota medan,
Sumatera utara
INDONESIA
Jurnal Sistem Komputer dan Informatika (JSON)
ISSN : -     EISSN : 2685998X     DOI : https://dx.doi.org/10.30865/json.v1i3.2092
The Jurnal Sistem Komputer dan Informatika (JSON) is a journal to managed of STMIK Budi Darma, for aims to serve as a medium of information and exchange of scientific articles between practitioners and observers of science in computer. Focus and Scope Jurnal Sistem Komputer dan Informatika (JSON) journal: Embedded System Microcontroller Artificial Neural Networks Decision Support System Computer System Informatics Computer Science Artificial Intelligence Expert System Information System, Management Informatics Data Mining Cryptography Model and Simulation Computer Network Computation Image Processing etc (related to informatics and computer science)
Articles 492 Documents
Penerapan Algoritma C4.5 Mengklarifikasi Penerimaan Bantuan Sosial Menggunakan Feature Selection M Wandi Dwi Wirawan; Siska Kurnia Gusti; Jasril Jasril; Pizaini Pizaini
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6653

Abstract

The Indonesian government's efforts to overcome poverty in Indonesia are through the Smart Indonesia Card (KIP) program which is carried out by the government in the form of providing assistance to underprivileged families. The main aim of distributing KIP assistance is to help send underprivileged children to continue their education, the difficulties found in receiving KIP are due to the large number of residents registering, as well as the data having several conditions, the limited time available in providing KIP by sub-district parties, the completion base is relatively low, therefore the provision of assistance must be right on target. Therefore, the aim of this research is to look for the most influential attributes in receiving KIP assistance in order to improve the results of the data verification process. After carrying out Feature Selection using Information Gain, the most influential attributes can be obtained. The influences are Number of Art, Number of Rooms, Cooking Room, Refrigerator, Motorbike. Therefore, we need to know some of the attributes that most influence the selection of KIP assistance so that we can get accuracy values from decision tree modeling using the C4.5 algorithm or decision tree. Test This experiment can produce a decision tree in which the Number of Art attribute is the most influential attribute with the success rate of KIP acceptance. This evaluation uses a confusion matrix to obtain an accuracy value of 98.21%, precision of 98.21%, recall of 99.48%.
Analisis Sentimen Ulasan Pelanggan Online Ubi Madu Cilembu Abah Nana Menggunakan Algoritma Naïve Bayes Muhammad Rafly Al Fattah Zain; Mia Kamayani
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6646

Abstract

This research aims to analyze the sentiment of online customer reviews for Ubi Madu Cilembu Abah Nana using the Naïve Bayes algorithm. The study has two main objectives: to classify the sentiment analysis of reviews into positive and negative categories regarding the service and products of Ubi Madu Cilembu Abah Nana, as well as to evaluate the accuracy level of the final classification results. The data was collected from online food delivery applications such as Gofood, Grabfood, and Shopeefood. The data used in this study amounts to 259 entries, with 310 positive and 49 negative data points. After conducting experiments, an accuracy result of 86.29% was obtained in Experiment 1 using the Split Data operator, and an accuracy of 86.12% was achieved in Experiment 2 utilizing Cross Validation with the assistance of language experts. The findings of this research indicate that the Naïve Bayes algorithm can be employed to classify customer sentiment towards the service and products of Ubi Madu Cilembu Abah Nana with a significantly high accuracy rate. These results can be valuable for Ubi Madu Cilembu Abah Nana in enhancing their service and product quality based on customer feedback. Additionally, this study also contributes to the field of sentiment analysis and natural language processing by applying classification algorithms to customer review data.
Implementasi Algoritma Knuth Morris Pratt Dalam Pencocokan String Pada Kamus Indonesia–Korea Rakhmat Kurniawan R; Aidil Halim Lubis; Siti Ayu Hadisa
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6149

Abstract

Currently, South Korean culture is very popular with many Indonesians, and the rapid development of Korean culture in Indonesia is currently very widespread and very popular. Many Indonesians even learn Korean to keep up with current trends, but due to the different structure of the language, learning Korean becomes more difficult for most people. The dictionary is an effective guide for translating foreign languages/terms. Conceptually, dictionaries are arranged alphabetically, along with explanations of definitions, uses or translations. This is also required for Indonesian to Hangul Korean translation. Many Indonesian-Korean dictionaries are currently published in printed form, but it is still difficult to use because users have to look up the meanings manually. We need practical and effective new media such as smartphone media. There are many algorithmic methods that can be used to create dictionary applications, one of which is using the Knuth Morris Pratt (KMP) algorithm. With this algorithm, every text to be translated is checked for word search and then a match is found with the appropriate word from the desired word. In this study, the final results of the study found differences in the use of the word hangul in formal and informal forms. In this study, the authors tested the application of the algorithm on an Android-based Indonesian-Korean dictionary application.
Sistem Antrian Pelanggan Menggunakan Metode Jackson Network Queue Mukhamad Niamaskur; Andi Widiyanto; Agus Setiawan
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6741

Abstract

Information systems can be applied in various fields either as the main means or to increase productivity or service quality. One of the uses of technology is that it is used as a means to make it easier for customers to place orders which aims to avoid queues that are too long. Setia Car Spare Parts Store is a provider of car spare parts that has many customers which sometimes makes the customer queue too much. This sometimes makes customers, especially new customers, impatient to queue. To make the queue more orderly, a queuing system will be built to maximize service and increase customer satisfaction which is calculated using the Jackson method. This method was chosen to calculate the time that is considered in accordance with what the customer expects. The queuing system applied to the system built is a single channel FIFO. From the results of system testing carried out, the application of a queuing system with online ordering by applying the Jackson method can enable employees to serve 48 customers in a day with an average of 15 minutes of service time. These results are more when compared to offline services where each employee can only serve 41 customers with an average service time of 17.56 minutes.
Metode TOPSIS Untuk Penerima Bantuan Pendidikan Bagi Mustahik Fakir Devit Satria; Desyanti Desyanti; John Suarlin
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6734

Abstract

Education is mandatory for all levels of society, every parent wants their children to be able to go to school properly, but the roots of education problems generally lie in financing for parents who have relatively low incomes. If conditions like this continue, Indonesia will lose the best generation if there are still many children who do not go to school due to the cost factor. The Dumai City National Amil Zakat Agency (BAZNAS) is one of the Amil Zakat Agencies in Riau Province. The Dumai City Baznas created an educational assistance program for poor families in the form of money to buy school supplies. Mustahik who wish to receive educational assistance must fill out a form and other predetermined conditions. After that, Baznas will select the incoming proposals and carry out the selection process. The large number of proposals caused Baznas to take a long time to make a decision because they had to check the submitted documents one by one, because it took a long time, the proposal for submitting assistance was approved based on the results of the meeting and agreement with the chairman of BAZNAS. So that the results decided are not as optimal as the actual conditions. For this reason, a system is needed that can assist BAZNAS in carrying out the document selection process in accordance with the requirements so that the assistance provided is right on target and can determine priorities for recipients of educational assistance for mustahik. The TOPSIS method is able to provide solutions to problems that occur, from the results of research conducted by Sutjiati Gita Lestari, it is ranked 1st with a value of 0.8041
Prediksi Harga Tandan Buah Segar dengan Algoritma K-Nearest Neighbor Silvi Joya Arditna Br Bukit; Rakhmat Kurniawan R.
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6818

Abstract

Palm oil and its derivative products are a source of foreign exchange for this country, because efforts are needed to maintain and develop the sustainability of palm oil as a potential natural resource. The company carries out statistical analysis on the factors inhibiting the previous month's harvest with a correction value of 5% – 12%. However, this kind of analysis still produces inaccurate prediction results, this is because the calculation process still involves estimation techniques from personal experience, looking at previous production patterns and other determining factors such as land area, principal amount and planting age. As a result, prediction targets often experience errors and production results are excessive or less than the target. Therefore, better predictive calculations are needed in determining palm oil production targets. Accurate predictions can help companies make decisions to increase production output. To carry out forecasting, it is necessary to apply the K-Nearest Neighbor Algorithm which can be used to predict palm oil prices in the future. Based on the results of data mining calculations using palm oil FFB prices from 2018 to 2023 (May 2023), it was concluded that the prediction of palm oil FFB prices in the 67th month (July 2023) had an accuracy level of 10,667 with k=3 and 19,200 with k=5.
Perbandingan Algoritma MOORA dan Profile Matching pada Sistem Pemilihan Pupuk untuk Tanaman Porang Farid Akbar Siregar; Fatma Sari Hutagalung; Mhd Basri
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6772

Abstract

Porang plants have long been utilized as a source of carbohydrates, fats, proteins, minerals, vitamins, and dietary fiber, which are exported as raw materials for various industries. In recent years, porang plants have become a highly profitable export commodity. One of the critical factors influencing porang plant production is fertilization. The timely, precise dosage, and correct method of fertilization determine the effectiveness of the fertilizer applied. MOORA considers various criteria in a balanced manner. Its ability to optimize the ratios between these criteria enables a more comprehensive selection of fertilizers. Profile Matching can be effective when specific criteria need to be emphasized over others. However, this method may not yield optimal decisions when several criteria carry significant weight. This research aims to determine the best type of fertilizer by applying a Decision Support System (DSS) and provides the benefit of assisting farmers in determining the most suitable fertilizer types for each phase of porang growth.In this study, a comparison was made between the MOORA and Profile Matching algorithms in the context of fertilizer selection for porang plants, using 7 fertilizer alternatives and 6 criteria types. Based on the research results, it can be concluded that both algorithms produce relatively similar outcomes, but the Profile Matching algorithm has a faster processing time compared to the MOORA algorithm in determining results. The contributions of this research include the development of a fertilizer selection system to help farmers optimize the growth and harvest of their crops. It also contributes to scientific literature and the comparison of algorithms, which can assist scientists and practitioners in selecting the most appropriate algorithms for similar problems in the future.
Facial Expression Recognition inCovid-19 Pandemic EraUsing 2 Stage Convolutional Neural Network Kevin Kurniawan; Lili Ayu Wulandhari; Antonius Rildo Pramudya Gondosiswojo
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6768

Abstract

In the Covid-19 pandemic era, the use of face mask has become mandatory for all citizens to prevent the spread of the virus. This regulation has becomes a big problem for the Facial Expression Recognitions (FER) applications because face mask cover more than halfof human faces. Starting from this problem, this experiment attemps to produce a robust network which can perform well in both conditions: recognizing expressions with and without a face mask. Dataset used in this experiment is FER2013, with a preprocessing step to produce a FER2013 masked. This research uses 2-stage network, where the first network is used to recognize whether the subject is wearing a mask or not, and then the second network is used to recognize the expression based on the result from the first stage. The network in this experiment is based on Convolutional Neural Network (CNN), with Imagenet as our pretrainedmodel and EfficientNet as our architecture model.Ourproposed model has shown quite good performance in recognizing expressions, even when the data consists of subjects who use and do not use masks with an accuracy of 57.55%.
Perbandingan Metode Dempster Shafer Dan Teorema Bayes Dalam Sistem Pakar Mendiagnosa Moyamoya Disease Naufal Rifqi; Agus Iskandar
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6819

Abstract

The main aim of this research is to compare two analytical approaches, namely the Dempster-Shafer Method and the Bayes Theorem, in the context of a system developed for diagnosing Moyamoya disease. Moyamoya is a rare condition involving the narrowing or blocking of blood vessels in the brain, which can lead to disrupted blood flow and an increased risk of stroke. In the medical field, diagnosing Moyamoya disease is a crucial initial step for appropriate treatment planning. The Dempster-Shafer Method is an approach used to address uncertainty and combine uncertain information into a conclusion. On the other hand, the Bayes Theorem is a statistical principle that connects the probability of a hypothesis before and after new evidence emerges. Both of these approaches are vital in the medical diagnostic process. In this study, both methods are implemented in an expert system specifically developed for diagnosing Moyamoya disease. Data from Moyamoya cases are used to evaluate the performance of both methods. Performance measurement is conducted by observing diagnostic accuracy, computational time, and resource usage. The results of this research provide valuable insights into the effectiveness and performance of the Dempster-Shafer Method and the Bayes Theorem in medical applications, particularly in diagnosing Moyamoya disease. Strengths and weaknesses of each approach are revealed, aiding in understanding situations where each method is most suitable. The Dempster-Shafer Method is effective in dealing with complex uncertainties and combining uncertain evidence. Meanwhile, the Bayes Theorem excels in probability calculations. The implications of this research are important in developing more advanced medical expert systems. In the medical realm, where diagnostic decisions impact patient care, a better understanding of these approaches helps in selecting the most appropriate method for specific situations. The results of comparing both methods indicate that the Dempster-Shafer Method yields a high probability of around 91%, indicating a substantial likelihood that the patient is suffering from this disease. Conversely, the Bayes Theorem yields a low probability of around 22%, suggesting a relatively small likelihood that the patient has Moyamoya Disease.
Sistem Pendukung Keputusan Rekomendasi Objek Wisata Menerapkan Metode MABAC dan Pembobotan ROC Fifto Nugroho; Agung Triayudi; Mesran Mesran
Jurnal Sistem Komputer dan Informatika (JSON) Vol 5, No 1 (2023): September 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i1.6822

Abstract

North Sumatra possesses abundant potential for tourist attractions, yet achieving the optimal selection of these attractions poses a challenge. Therefore, a decision support system is required to aid in the decision-making process for choosing the most suitable tourist attractions. In this study, the Multi Atributive Border Approximation Area Comparison (MABAC) method is employed to rank tourist attractions based on predefined criteria. MABAC combines geometric approaches with boundary approximation area comparison analysis to calculate priority scores for each tourist attraction. Additionally, the Rank Order Centroid (ROC) method is used to assign weights to the identified criteria. This research reveals various issues in the selection of tourist attractions in North Sumatra, such as complex criteria, variations in criteria weights, and insufficient tools to address these challenges. The primary objective of this study is to develop a decision support system capable of assisting stakeholders in selecting tourist attractions aligned with their preferences and objectives. The outcome of this research is the development of an efficient decision support system to aid in the selection of tourist attractions in North Sumatra. This system reduces subjectivity in decision-making, provides more accurate ranking based on established criteria, and assists stakeholders in understanding the process of selecting tourist attractions in a more transparent manner. The implications of this research include enhancing the quality of decision-making in the tourism industry and optimizing the utilization of tourist attraction potential in North Sumatra. As for the tourism recommendation with the highest rank, alternative 3 is obtained with a value of 0.6343, namely Paropo natural tourism.