cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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)
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : -     EISSN : 2685998X     DOI : https://dx.doi.org/10.30865/json.v1i3.2092
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
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)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 457 Documents
 33   34   35   36   37 
Klasifikasi Sinyal EEG Untuk Mengenali Jenis Emosi Menggunakan Deep Learning Rosemari, Pita; Rini, Dian Palupi; Sari, Winda Kurnia
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7172

Abstract

This research focuses on in-depth exploration and analysis of the application of three types of deep learning, namely Convolutional Neural Networks (CNN), Bidirectional LSTM (BI-LSTM) and Deep Neural Network (DNN). The three models are trained with the same parameters, consisting of three layers, using the Relu activation function, and applying 1 dropout level. In order to compare the performance of the three, experiments were carried out using three dataset groups for training and evaluation of performance. The evaluation includes metrics such as accuracy, recall, F1-Score, and areas under the curve (AUC). The dataset used is EEG Emotion which consists of 2458 unique variables. In terms of performance, BI-LSTM succeeded in outperformed the performance of CNN and DNN in the task of classification of emotional data based on EEG signals. On the other hand, CNN and DNN show excess in the acceleration of the training process compared to BI-LSTM. Although the accuracy of the two methods is almost similar in all data distribution, but in the evaluation of the ROC curve, the BI-LSTM model demonstrates superior with a more optimal curve than CNN and DNN.
Analisis Dan Visualisasi Data Penjualan Menggunakan Exploratory Data Analysis dan K-Means Clustering Sari, Shinta Permata; Putri, Raissa Amanda
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7180

Abstract

Many innovations in the retail sector are closely related to digitalization and technological advances. The value of sales data is increasing as a resource for businesses in today's digital era. Sales data consists of details about the items sold, the clients they serve, sales patterns, and other elements that influence how well a business operates. However, effectively handling and understanding vast and complex sales data can be difficult and confusing. So with this problem the author will determine the annual sales level of the products that are most widely marketed by applying Exploratory Data Analysis (EDA) and the K-Means Clustering Algorithm, the method used is to determine the sales level based on the attributes used, the sales level will later be divided into 3, namely clusters 1 is high, cluster 2 is medium and cluster 3 is low. Based on the results of the EDA and K-Means methods, the results of a sales comparison for 4 years have a average value, indicating that sales in 2019 have large average values between 2020, 2021 and 2022. From the visualization results it can be concluded that there are 27 products in the cluster-1 category, 10 products in the cluster-2 category, and 5 products in the cluster-3 category.
Penerapan Algoritma K-Nearest Neighbor Untuk Pengelolaan Efisien Tata Letak Buku Dalam Lingkungan Perpustakaan Dollar, Dzulfikri Akbar; Zufria, Ilka
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7181

Abstract

The library plays a central role in providing efficient access to information tailored to the interests of the community. The current system of organizing the library at the Medan City Library and Archives Department involves using call numbers. This system isn't very efficient for readers looking for interesting books, which can decrease people's interest in reading and perceive the library as a dull place. Hence, researchers have attempted to optimize book layout by prioritizing the most popular books. Using the K-Nearest Neighbor algorithm to optimize the book layout at the Medan City Library and Archives Department can assist in arranging book patterns based on historical borrowing data and facilitate better access to collections favored by library visitors. The research method involves collecting book borrowing data from previous months and processing it using the K-Nearest Neighbor Algorithm with Euclidean Distance calculation. The research results demonstrate that implementing this algorithm successfully predicts book arrangement patterns that align with reader interests. An adaptively arranged layout enhances the availability of popular books in easily accessible areas of the library for visitors. This is evident from the research findings in May, where the priority for the following month was the general collection. Similarly, in June, the priority was indeed the general collection, confirming that the algorithm's use of K-Nearest Neighbor is successful in optimizing book layout.
Implementasi Data Mining Dalam Memprediksi Penjualan Parfum Terlaris Menggunakan Metode K-Nearest Neighbor Sabda, Mhd Angga; Suhardi, Suhardi
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7194

Abstract

Ahlinyaparfum is a perfume shop that provides various kinds of fragrance oils. To run his business, Ahlinyaparfum must send perfume variants to his shop from the place where the perfume is made, which requires shipping costs. Often, the perfume variants offered by Ahlinyaparfum do not match the wishes of customers, which has a negative impact on the number of store sales. The best-selling prediction process is needed based on previous sales data to help stores know which perfumes are most popular with customers and the level of best-selling in the future. By applying data mining using the K-Nearest Neighbor method, this research aims to overcome this problem. This method was tested using perfume sales data from January to June 2023 with a total of 215 data. To test and ensure its performance with the help of the Jupyter Notebook application with Python. The process of predicting perfume sales for the next month uses the parameter k = 3 with Euclidean distance calculations. The best-selling result predicted for the 7th month is Aigner Blue Emotion with total sales of 153 ml. Based on the evaluation algorithm, the overall average value of MSE is 0.52, which shows that the results are very good in determining next month's perfume sales. This is due to the fact that the calculation results are closer to the actual value the lower the MSE value.
Penerapan Algoritma Naïve Bayes Terhadap Klasifikasi Penerima Bantuan Program Keluarga Harapan (PKH) Irsyada, Amelia; Haerani, Elin; Irsyad, Muhammad; Wulandari, Fitri; Afriyanti, Liza
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7203

Abstract

Poverty in Indonesia is one of the complex social issues. As a manifestation of the government's concern about poverty in the country, various assistance programs have been established to target the impoverished population. One such program aimed at alleviating poverty in Indonesia is the Family Hope Program (Program Keluarga Harapan or PKH). PKH is a conditional cash transfer program provided to the impoverished community. The manual selection process for aid recipients is considered less than ideal, leading to issues of improper distribution. In this study, the Naïve Bayes algorithm is applied to classify PKH aid recipients in the Bungaraya Subdistrict, Siak Regency, as part of the government's efforts to tackle poverty. The dataset used consists of 560 records, including data on existing PKH aid recipients and potential recipients from various villages in the Bungaraya Subdistrict for the year 2022. The attributes considered in this research include age, income, number of dependents, dependents attending school, dependents with disabilities, housing status, floor type, and wall type. The highest accuracy obtained through calculations on Google Colab is 99% for an 80:20 ratio, while the accuracy obtained using RapidMiner is 94%.
Pemanfaatan Algoritma K-Means Dalam Menentukan Potensi Hasil Produksi Kelapa Sawit Wahyuni, Ayu Sri; Haerani, Elin; Budianita, Elvia; Afrianti, Liza
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7226

Abstract

Considering the importance of oil palm cultivation now and in the future, as well as the increasing demand for palm oil by the world population, it is necessary to think about efforts to increase the quality and quantity of palm oil production appropriately in order to achieve the desired and achievable goals. Based on data on palm fruit production results from PT Salim Ivomas Pratama Tbk, it can be seen that fruit production varies in several places. The potential yield of oil palm fruit is based on the harvested area, actual production and year of planting. K-Means welding can help identify the potential of oil palm, with results that vary from day to day. This process allows locations with similar production patterns, which facilitates management decisions and production strategies. In this research, potential fruit planting areas were grouped using the K-Means algorithm. K-Means aims to facilitate the grouping of blocks with high and low fruit production. The data used is 180 data for the last 5 years, namely from 2018 to 2022, with the attributes Harvest Block, Area, Sheet Weight, and Product Realization or quantity. This research uses the help of Rapidminer and Google Colab software. The results of this research show that C1 (the highest) is 125 Harvest Block data in the sense that the first group is included in the good or high harvest yield category in 2018-2022, and C0 (the lowest) is 55 Harvest Block data in the sense that the second group is included low yield category 2018-2022.
Pemilihan Paket Wisata One Day Tour Menggunakan Model Pendukung Keputusan TOPSIS Singgalen, Yerik Afrianto
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7231

Abstract

The development of Labuan Bajo tourism attracts foreign and domestic tourists to explore various natural beauties through fun activities. Tour agents provide a variety of interesting activities and tourist visits to the islands around Labuan Bajo that can provide new experiences for tourists. The activities are sold through One-day tour packages in Labuan Bajo. Still, depending on the service provider, the itinerary description, admission ticket,  and order of visit to the destination are very complicated. Considering this, this study uses the TOPSIS decision model in choosing One Day Tour tour packages in Labuan Bajo by considering the criteria of price, destination, duration, admission ticket, and service rating. Based on the results of this study, it can be seen that the highest preference value from the ranking results is the Full Day Trip to Explore 6 Destinations in Labuan Bajo and Komodo tour package, with a value of 0.673056111. Furthermore, the tour package that occupies the second position from the ranking results is the 1-day Komodo island Tour hopping around by Speed Boat with a preference value of 0.628303746. Meanwhile, the tour package that occupies the third position from the ranking results is One day Komodo trip with Bintang Komodo Tours with a  preference value of 0.53181476. This shows that the TOPSIS method produces recommendations for One Day Tour packages in Labuan Bajo for tourists by considering the price of tour packages, the number of destinations visited, the length of time or duration of tourist time, admission tickets in tour packages, and ratings The services of the travelers were previously related to the tour package. Thus, the selection of TOPSIS-based One Day Tour tour packages can minimize the risk that causes misunderstandings or tourist dissatisfaction related to the tour packages prepared by each travel agent.
Analisis Sentimen Ulasan Pengguna Game Pubg Di Google Play Store Menggunakan Algoritma Naïve Bayes Wibowo, Fajar Iqbal; Febriandirza, Arafat
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 3 (2024): Maret 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i3.7264

Abstract

In today's digital era, technological development is very rapid and sophisticated. The online gaming industry has also evolved. Online games are a variant of video games that are played online via the internet. When users connect with other users, users can interact and work together. Battle rolaye games, such as Player Unknown's Battlegrounds (PUBG) have become one of the most popular of the many online games available. PUBG games offer a large-scale gaming experience that creates a dynamic gaming experience. One of the advantages of the PUBG game is that it has an attractive visual design and high quality graphics so that the game feels more realistic. However, this cannot guarantee satisfaction for users. To find out user sentiment towards the PUBG game, sentiment analysis using the Naïve Bayes Algorithm is carried out which aims to find out how accurate the Naïve Bayes Algorithm is used in classification. Data is taken using web scrapping techniques as many as 1000 user reviews in the Google Play Store review column. After going through preprocessing, the data is divided into 50% training data and 50% testing data. Prediction results tend to be positive with 578 positive sentiments and 232 negative sentiments. Based on evaluation using confusion matrix, the results are 83.95% for accuracy, 88.10% for precision, and 89.62% for recall.
Perbandingan Metode ARAS dan MOORA dalam Seleksi Penerimaan Pegawai Baru Non ASN Susanto, Susanto; Ningrum, Setya; Cahyono, Yudi
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 3 (2024): Maret 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i3.7449

Abstract

The acceptance of new non-ASN candidates is a major problem in recruiting new employees, this happens because of the large number of new prospective employees who register and the number of vacancies that are inadequate, therefore research is carried out that aims to create a decision support system that can speed up the process of recruiting candidates. new employee. The methods used in this research are ARAS (Additive Ratio Assessment) and MOORA (Multi-Objective Optimization on the basis of Ratio Analysis) methods. The selection of this method is able to filter out the most alternatives based on weighting and this method is able to choose goals based on different criteria, namely benefits and costs. The results obtained from the ARAS method are the calculation rankings from the comparison of alternative utility functions with the optimal utility function values, while the results obtained from the MOORA method are the calculation rankings of the maximum and minimum values. From this value, an alternative that meets the criteria through calculations using the ARAS and MOORA methods, the employee alternative chosen is Yuniar Pilakso Angkasa with a final result of 0.935 for the ARAS method and 0.163 for the MOORA method. The results of the Spearman Rank coefficient test obtained a value of 0.9357% for the ARAS method and 0.7428% for the MOORA method, meaning that the two methods have a strong correlation level and can be used in recruiting new non ASN employees.
Klasifikasi Sentimen Terhadap Topik Pindah Ibu Kota Negara Pada Twitter Menggunakan Metode Naïve Bayes Classifier Dermawan, Jozu; Yusra, Yusra; Fikry, Muhammad; Agustian, Surya; Oktavia, Lola
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 3 (2024): Maret 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i3.7475

Abstract

Towards the middle of 2019, President Joko Widodo announced plans to relocate Indonesia's capital city. This caused pros and cons in the community, which were widely observed in various social media. To quickly measure the level of public sentiment towards the policy of moving the National Capital City (IKN), whose construction is already underway, a classification system that has good performance is needed. This research proposes a classification of public sentiment on the topic using the Naïve Bayes Classifier method. The data used in this study amounted to 4000 tweets that have been classified into two classes, namely 2000 positive class data and 2000 negative class data. The purpose of this research is how to apply the Naïve Bayes Classifier method in classifying sentiment on the topic of moving the nation's capital and determine the accuracy level of the method. The application of the Naïve Bayes classification method using TF-IDF features to classify 10% of the data as testing data resulted in an accuracy of 77.00%, for a precision value of 77.06%, recall 77.08% and f1-score of 77.00%. Based on the results achieved, the Naïve Bayes Classifier method is good at text classification tasks, with a fairly good accuracy rate.

Page 35 of 46 | Total Record : 457

 33   34   35   36   37 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol. 7 No. 2 (2025): Desember 2025 Vol. 7 No. 1 (2025): September 2025 Vol 6, No 4 (2025): Juni 2025 Vol. 6 No. 4 (2025): Juni 2025 Vol. 6 No. 3 (2025): Maret 2025 Vol 6, No 3 (2025): Maret 2025 Vol. 6 No. 2 (2024): Desember 2024 Vol 6, No 2 (2024): Desember 2024 Vol. 6 No. 1 (2024): September 2024 Vol 6, No 1 (2024): September 2024 Vol 5, No 3 (2024): Maret 2024 Vol. 5 No. 3 (2024): Maret 2024 Vol. 5 No. 2 (2023): Desember 2023 Vol 5, No 1 (2023): September 2023 Vol 4, No 4 (2023): Juni 2023 Vol 4, No 3 (2023): Maret 2023 Vol 4, No 2 (2022): Desember 2022 Vol 4, No 1 (2022): September 2022 Vol 3, No 4 (2022): Juni 2022 Vol 3, No 3 (2022): Maret 2022 Vol 3, No 2 (2021): Desember 2021 Vol 3, No 1 (2021): September 2021 Vol 2, No 3 (2021): Mei 2021 Vol 2, No 2 (2021): Januari 2021 Vol 2, No 1 (2020): September 2020 Vol 1, No 3 (2020): Mei 2020 Vol 1, No 2 (2020): Januari 2020 Vol 1, No 1 (2019): September 2019 More Issue