cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josyc@gmail.com
Editorial Address
Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer System and Informatics (JoSYC)
ISSN : 27147150     EISSN : 27148912     DOI : -
Journal of Computer System and Informatics (JoSYC) covers the whole spectrum of Artificial Inteligent, Computer System, Informatics Technique which includes, but is not limited to: Soft Computing, Distributed Intelligent Systems, Database Management and Information Retrieval, Evolutionary computation and DNA/cellular/molecular computing, Fault detection, Green and Renewable Energy Systems, Human Interface, Human-Computer Interaction, Human Information Processing Hybrid and Distributed Algorithms, High Performance Computing, Information storage, Security, integrity, privacy and trust, Image and Speech Signal Processing, Knowledge Based Systems, Knowledge Networks, Multimedia and Applications, Networked Control Systems, Natural Language Processing Pattern Classification, Speech recognition and synthesis, Robotic Intelligence, Robustness Analysis, Social Intelligence, Ubiquitous, Grid and high performance computing, Virtual Reality in Engineering Applications Web and mobile Intelligence, Big Data
Articles 443 Documents
Penerapan Naive Bayesian Classifier Dalam Penyeleksian Beasiswa PPA Cici Alfiani Pradika Dita; Putri Chairunisyah; Mesran Mesran
Journal of Computer System and Informatics (JoSYC) Vol 2 No 2 (2021): February 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In this study, the author uses the Naïve Bayes Classifier method to classify scholarship recipients at Budi Darma University. The use of the Naïve Bayes Classifier method was chosen to make decisions in order to determine whether students enrolled in the scholarship program were accepted or rejected. The classifier method is to classify text based on the highest probability that it is defined as a new document category. From the results of this research, the results show that the value of "Receiving" is higher than "No", which is 0.0351 compared to 0, so it can be concluded that the student on behalf of Riska Ramadhani received the PPA 2019 scholarship.
Implementasi Algoritma Backpropagation Dalam Memprediksi Jumlah Penduduk Usia Produktif Pada Kota Pematangsiantar Mhd Ridho Azhar; Sumarno Sumarno; Indra Gunawan
Journal of Computer System and Informatics (JoSYC) Vol 2 No 2 (2021): February 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The productive age itself is a population in the age group between 15 to 64 years, whether they work, go to school, and take care of the household, in this case individuals who are in the scope of productive age are people who can still work well to produce a product and services. This study uses an Artificial Neural Network (ANN) with the backpropgation method. The backpropagation algorithm is one of the existing methods of neural networks as a prediction, estimation, classification, and pattern recognition algorithm. The research data is secondary data sourced from the Central Statistics Agency (BPS) from 2013 to 2015. The data is divided into 2 parts, namely training and testing data. There are 5 architectural models used in this study. 2-20-1, 2-21-1, 2-22-1, 2-23-1, 2-24-1. Of the 5 architectural models used, the best 1 model is obtained, namely 2-24-1 with an accuracy level of 80%, MSE 0.00085177 and epoch 100. So this model is good for predicting the number of productive age population in the city of Pematangsiantar in the future
Algoritma Backpropagation Dalam Melakukan Estimasi Penjualan Beras Pada CV Hariara Pematangsiantar Ruri Eka Pranata; Indra Gunawan; Sumarno Sumarno
Journal of Computer System and Informatics (JoSYC) Vol 2 No 2 (2021): February 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The need for rice is an important factor in Indonesia where people make rice as a staple food source. Pematangsiantar city has a rice mill and rice sale, one of which is CV Hariara Pematangsiantar. Every year the amount of rice in CV Hariara Pematangsiantar changes. Therefore a prediction is needed to determine the amount of rice sales that will come and this prediction will be useful for the company to increase rice sales in the future. The data to be predicted is data on the amount of rice sales in CV Hariara Pematangsiantar in 2014-2017. The algorithm used to make predictions is a backpropagation neural network. There are five architectural models used in this prediction namely, 2-25-1 has an accuracy rate of 60%, 2-32-1=40%, 2-47-1=80%, 2-50-1=80%, and 2-52-1=60%. The best architecture of the five models is 2-47-1 with an accuracy of 80% and MSE of 7,46434101. So this architectural model is good enough to predict the amount of rice sales in CV Hariara
Estimasi Pemberantasan Hama di Kebun Bah Jambi Menggunakan Algoritma Backpropagation Agung Bimantoro; Sumarno Sumarno; Heru Satria Tambunan
Journal of Computer System and Informatics (JoSYC) Vol 2 No 2 (2021): February 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Oil palm, which is the largest palm oil producer, plays an important role in the welfare of the people in Indonesia because it creates many jobs. Oil palm plants cannot be separated from pests. The number of pest attacks on oil palm plants can cause a decrease in fruit production and can even cause the plant to die. In this study, the authors estimated the number of pest attacks in the oil palm plantation Unit Bah Jambi, North Sumatra using the backpropagation algorithm. The data used in this study were obtained directly from the Plantation Unit Bah Jambi plantation. In this study the authors used 5 architectural patterns; 2-10-1, 2-12-1, 2-14-1, 2-16-1, 2-16-1. Of the five architectural patterns used, the best architecture is obtained with an accuracy rate of 75%, 187 epoch iterations in 4 seconds, namely the 2-10-1 architectural pattern
Prediksi Hasil Produksi Kelapa Sawit PTPN IV Bahjambi Menggunakan Algoritma Backpropagation Venny Vidya utari; Anjar Wanto; Indra Gunawan; Sumarno Sumarno; Zulaini Masruro Nasution
Journal of Computer System and Informatics (JoSYC) Vol 2 No 3 (2021): Mei 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Oil palm is a tropical plant of the Indonesian natural palmae group which has a tropical climate. The growth and harvest of oil palm also depends on fertilizers and the rainfall that falls every day. To get good production results it requires high ability and a lot of labor. Each production result certainly does not always increase, there must be a time when the production will decrease, therefore an algorithm is needed to predict it so that companies can find out the development of palm oil production in the future. In this study, researchers used the Backpropagation Algorithm. The Backpropagation Algorithm is an algorithm that functions to reduce the error rate by adjusting the weight based on the desired output and target, there are 5 training and data testing architectural models, namely 2-21-1, 2-22-1, 2-24-1, 2-26 -1 and 2-28-1. From the results of testing data on oil palm production, the best architectural model is obtained, namely 2-22-1 which shows that the target is reduced by the output that SSE is 0.35206024, from the data obtained, the performance of the calculation of artificial neural networks with the Backpropagation Algorithm gets an accuracy of 83.3%. . So that it can be used as a benchmark in predicting palm oil production, seen from the comparison of the desired target with the predicted target
Analisa Datamining dengan Metode Klasifikasi C4.5 Sebagai Faktor Penyebab Tanah Longsor Afrialita Widiastari; Solikhun Solikhun; Irawan Irawan
Journal of Computer System and Informatics (JoSYC) Vol 2 No 3 (2021): Mei 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Landslides are geological events where soil movement occurs such as falling rocks or large lumps on the ground. Landslides often occur when it rains, although not always. In addition, landslides generally occur in areas with steep slopes. With the C4.5 method it can be used to classify data that has numeric and categorical attributes. The results of the classification process in the form of rules can be used to predict the value of the discrete type attribute from a new record. Data obtained from the National Disaster Management Agency regarding the factors causing landslides can produce an accuracy value of 77.78%, meaning that the resulting rules or rules are close to 100%, it can be concluded that to classify the factors causing landslides using C4.5 by looking at the node the highest is slope. To find out these factors can provide input to the Disaster Management Agency to be more concerned with the factors that caused the landslides
Rancang Bangun Sistem Penjualan Furniture Menggunakan Metode Exponential Smoothing Ambarwati Ambarwati
Journal of Computer System and Informatics (JoSYC) Vol 2 No 4 (2021): Agustus 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v2i4.816

Abstract

Furniture Agung is an MSME engaged in furniture located in the district of Semarang. MSMEs are still conducting data collection, processing and transactions that are carried out manually. This process becomes ineffective and inefficient because errors can occur in recording and data can be lost. This research aims to design an information system for furniture sales and sales forecasting using the exponential smoothing method in September 2020 to May 2021. Based on the results of sales analysis testing using the exponential smoothing method using alpha 0.2 in May 2021, the calculation of forecasting demand for furniture products as many as 41 pieces. The results of calculations using mean square error (MSE) alpha 0.2 to predict the error rate of furniture demand are: 69.22 = 69. This system research uses a codeigniter framework, and MySql as a database server. The design of the web-based system is expected to make it easier for MSMEs to conduct digital transactions and manage goods data so that data reports can be known easily, quickly, accurately, and data is stored safely
Implementasi Pisanc Chiper Untuk Autentikasi Voice Chat Muhammad Fajar Rizky; Muhammad Syahrizal; Soeb Aripin
Journal of Computer System and Informatics (JoSYC) Vol 2 No 4 (2021): Agustus 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v2i4.819

Abstract

In securing voice messages, information sent through the internet network must be authenticated for its authenticity, data content, delivery time, and so on. To prevent data manipulation by irresponsible parties, the creation of a data leak that has a negative impact. The occurrence of data leaks that most users are still not aware of. This can happen due to the lack of security of the message itself which results in problems that arise and also losses by certain authoritarian parties. The solution in securing voice messages using modern cryptographic techniques that have been combined with NRZI encoding and the Feistel network by Pisanc Cipher, is a way to maintain the authenticity and accuracy of data or authentication in voice messages. It is useful to look for the characteristics of good encryption, namely confusion and diffusion. This results in a higher level of security. By using the Pisanc Cipher method to secure voice messages, it can generate security and authenticate data to prevent data leakage. In addition, another benefit of using the Pisanc Cipher method is to maintain the authenticity of voice messages.
Penerapan Metode Inner Product Pada Aplikasi E-Diagnosa Agranulositosis Enrio Situmeang
Journal of Computer System and Informatics (JoSYC) Vol 2 No 4 (2021): Agustus 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v2i4.823

Abstract

An expert system (expert system) is a system that seeks to adopt human knowledge to computers, so that computers can solve problems like experts. The large number of people affected by orthopedic disease and the lack of orthopedic specialists make it difficult for orthopedic specialists to handle a large number of patients. One way to solve this problem is to create an expert system for diagnosing orthopedic diseases. Orthopedic disease diagnosis expert systems can help experts as reliable assistants with the aim of helping patients to continue to receive treatment even though experts are not available. This expert system can certainly solve a problem about Otopaedics by imitating the workings of an Orthopedic specialist. The inner product method is used for initial diagnosis by inputting the patient's symptoms. The result of the inner product process is taken as the highest value as the output in the form of the name of the disease and the type of patient treatment. If the highest value generated from the inner product process is more than one and the symptoms of the disease have a quantity and time value, it will proceed to further diagnosis using the certainty factor method, by inputting the length of time for each symptom, or the quantity of symptoms to determine the value of confidence in a particular symptom. disease based on the duration of each symptom and the quantity of these symptoms.
Pengaruh Point Vuforia Object Scanner Terhadap Karakteristik 3D Object untuk Menampilkan Informasi Berbasis Augmented Reality Putri Mandarani; Agung Putra Wilis; Ganda Yoga Swara
Journal of Computer System and Informatics (JoSYC) Vol 2 No 4 (2021): Agustus 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v2i4.826

Abstract

Augmented Reality (AR) applications are one of the current mobile app trends. Its ability to display information as if to make the user merge with the information provided. The specialty of the application is in the marker. One marker that is in great demand is known as markerless, such as 3D Object Tracking. In making this 3D Object-based AR application, one must pass a stage where a real object is taken at points or known as points to be used as markers. The application used at this stage of making markers is known as the vuforia object scanner. From the experience of making AR applications, it was found conditions where markers with a large number of points were not able to display information properly, a small number of points were able to display information well and sometimes the two conditions were opposite or comparable, i.e. a lot of points makes a good marker and a few points make a bad marker. This inconsistent condition becomes a problem in this study. The test results show that the points do not affect the marker's ability to display information, but are influenced by the characteristics of the object used as the marker. Tests conducted on randomly selected objects resulted in 2 parameters to be tested in this study, namely the texture and pattern of the object. Markers with good quality to be used as markers for 3D objects are markers with a hard texture, with a detection angle of 90° and 135° and with a regular pattern

Page 9 of 45 | Total Record : 443