cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Elsa Aditya
Contact Email
redaksijurnalupu@gmail.com
Phone
+6285175205250
Journal Mail Official
redaksijurnalupu@gmail.com
Editorial Address
JL. KL. Yos Sudarso Km. 6,5 No. 3A, Tanjung Mulia, Medan, Sumatera Utara, 20241
Location
Kota medan,
Sumatera utara
INDONESIA
CSRID
Published by Universitas Potensi Utama
ISSN : 20851367     EISSN : 2460870X     DOI : https://doi.org/10.22303/csrid
Core Subject : Science,
Computer Science & IT
CSRID (Computer Science Research and Its Development Journal) is a scientific journal published by LPPM Universitas Potensi Utama in collaboration with professional computer science associations, Indonesian Computer Electronics and Instrumentation Support Society (IndoCEISS) and CORIS (Cooperation Research Inter University).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 45 Documents
 1   2   3   4   5 
Komparasi Algoritma Data Mining Sebagai Prediksi Harapan Hidup Pasien Gagal Jantung: Komparasi Algoritma Data Mining Sebagai Prediksi Harapan Hidup Pasien Gagal Jantung Agustiena Merdekawati
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.188-202

Abstract

The heart is the most vital organ of the body. Heart failure is the leading cause of death with the largest number of cases. Therefore, it is necessary to estimate the biggest factor in life expectancy in patients with heart failure, so as to reduce mortality. In predicting the life expectancy of heart failure by using Knowledge Discovery in Database (KDD) it is possible to find predictive patterns of life expectancy for heart failure, so that it can reduce mortality. In this study using the C4.5 algorithm and the C4.5 algorithm with PSO (Particle Swarm Optimization) to obtain a predictive pattern of life expectancy for heart failure which then obtained the percentage of precision, recall and accuracy. This research is to produce a predictive pattern of life expectancy for heart failure with the criteria for the length of time the action has a top priority. By using the C4.5 algorithm, an accuracy of 73.33% is obtained, while using the C4.5 and PSO algorithms an accuracy of 99.00% is obtained, so it can be concluded based on the accuracy level that the C4.5 and PSO algorithm modeling has a higher accuracy than the C4.5 algorithm. . By using the C4.5 algorithm, the ROC graph accuracy is 0.897%, while using the C4.5 and PSO algorithms the ROC graph accuracy is 1.00%, so it can be concluded based on the ROC graph accuracy level that the C4.5 and PSO algorithm modeling has more accuracy. higher than the C4.5 algorithm.
Menghitung Akurasi Sistem Deteksi Masker Berdasarkan Arah Pandangan Kepala Objek Furqan Rasyid; Mar'atuttahirah; Muhammad Syukri Mustafa; Andi Asvin Mahersatillah Suvardi
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.203-214

Abstract

During this Covid-19 pandemic, the use of masks is highly recommended. The use of masks is very good to stop the spread of the virus. This is why many studies have created systems to assist humans in detecting the use of masks. However, from several existing studies, no research has been found that measures the accuracy of the detection system based on the direction of the object's head view, especially those using the fourth version of yolo (yoloV4). This study calculates accuracy based on 5 viewing angles, namely: (0, 45, 90) degrees sideways, up, and down. The distance between the camera and the test object is 1 meter. The results of the calculation, obtained very satisfactory results, namely 100% for each point of view. While the time required for the system to detect the fastest when the head position is straight ahead (0 degrees) with a time of 3.09 seconds. The longest time occurred when the head down position was 3.89 seconds
Sistem Informasi Kelayakan Pemberian Pinjaman dengan Metode Analitycal Hierarchy Process (AHP) Nurhadi nurhadi; Dede Yusminandar; Khabibillah; Muhammad Khaerudin
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.215-227

Abstract

The analysis process of selecting the feasibility of providing loans to creditors, sometimes they still use calculations and analyze estimates. This results in inaccurate decision making. In this study the authors make a Decision Support System as a basis that aims to provide decision support to the administration to determine customers in determining lending based on the data submitted by the prospective customer on the registration form. So that the lender is more efficient and effective in their work, prospective customers can simulate the amount that will be obtained through a web-based online application. The AHP (Analitycal Hierarchy Process) method will process the data and analyze it so that it issues the criteria ranking value. The information generated is in the form of information that has been manipulated by the system to determine whether or not members are eligible for a loan, as well as the appropriate amount based on the members' income and guarantees listed in the application form. This system can also be actually used by users and can be used easily because in its development it uses a prototype method which in its development involves users
Sistem Pendukung Keputusan Pemilihan Proyeketor Menggungakan Metode Weighted Aggregated Sum Product Assessment Rini Nuraini
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.228-241

Abstract

A projector is a device that can project the display from a computer or laptop onto a screen to make it look bigger. Projectors have many benefits including as a presentation tool, as an information medium, entertainment media and so on. How important the function of the projector is that there are many brands or brands of projectors that offer various capabilities and specifications. This becomes a problem because someone sometimes does not have knowledge of the projector specifications that suit their needs. The main objective of this research is to develop a decision support system for selecting projector equipment using the Aggregated Sum Product Assessment (WASPAS) method, in order to obtain the best alternative that suits the needs of several alternatives and certain criteria. The WASPAS method is able to solve multi-criteria problems through optimization of the analysis to get the best alternative. The DSS developed is based on a website, with the main features including managing criteria and weight data, alternative data, conducting alternative assessments, calculating processes using the WASPAS method and displaying the best alternative in the form of ranking. In addition, the developed system produces valid WASPAS method calculations, because the results are in accordance with manual calculations. Based on the test through the black-box testing method, it shows that the developed system has been running well.
Rancang Bangun Sistem Kontrol Watermeter PDAM Berbasis IoT Mukhsin Mukhsin; Muh Pauzan; Nuhasanah
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.242-257

Abstract

The process of checking or monitoring (control system) of water use to each customer every month which has been carried out by the Officers of the Regional Drinking Water Company (PDAM) in its implementation still uses a manual system. In the implementation of monitoring, there are often errors in recording water use, namely different calculations on the same use (Human Error). This study aims to monitor water usage digitally using an IoT (Internet of Things) based watermeter. This study uses the Root Mean Square Error (RMSE) method as a model selection tool based on the error of the estimation results. The variable used is a 1 liter measuring cup where the glass will be measured by the value read on the watermeter. The test uses a national standard calibration with a value of 6,5, with a total of 30 tests. The results of the study were carried out on 10 experiments with samples of 0,005 m3, 0,01 m3, and 0,015 m3, respectively. The results of the research on the accuracy value owned on the sample of 0,015 m3 are said to be accurate because based on the calculation scale of the RMS theory, the smaller the accuracy value, the more accurate the value issued on the watermeter tool.
Komparasi Algoritma Decision Tree, Naive Bayes dan KNN dalam Klasifikasi Kanker Payudara Muhammad Abdul Jabbar; Erfan Hasmin; Sunardi; Cucut Susanto; Wilem Musu
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.258-270

Abstract

Breast cancer is a type of cancer that is commonly formed in breast cells and the cancer cells grow out of control. Cancer can occur in all genders. In 2020, the Global Cancer Observatory recorded a death rate of 684,996,000 and new cases of 2,261,419[1]. From the mortality rate, both men and women should be aware of their health by taking actions such as early detection and avoiding the risk of causing cancer. The source of data in this study came from the UCI Machine Learning Repository. This study aims to compare three data mining algorithms for classifying breast cancer. In this study, the algorithms used in making comparisons are the Decision Tree Algorithm, Naive Bayes, and KNN using 2 cross-validation methods, Hold-Out and K-Fold. The results of the test showed that the KNN algorithm always produced excellent accuracy performance compared to the Naive Bayes and Decision Tree algorithms, namely 98% in the Hold-Out method and 96% in the K-Fold method, while Naive Bayes is 95% on the Hold-Out method and 95% on the K-Fold method, Decision Tree is 94% on the Hold-Out method and 93% on the K-Fold method. Keywords—Breast Cancer, Decision Tree, Naive Bayes, KNN
Perbandingan Logistic Regression, Random Forest, dan Perceptron pada Klasifikasi Pasien Gagal Jantung Taufik Zulhaq Jasman; Erfan Hasmin; Sunardi; Cucut Susanto; Wilem Musu
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.271-286

Abstract

According to WHO (World Health Organization) data, heart disease accounts for one-third of all fatalities worldwide. Heart failure causes the death of approximately 17.9 million people worldwide and is more prevalent in Asia. With the use of technology, biostatistical analysis data may be processed using data mining techniques to uncover correlation patterns for each data from previous data that can then be used to forecast diseases based on these patterns. Algorithms with high accuracy can at least help medical experts prevent heart failure deaths. The ultimate goal of this research is to compare the algorithms and methods of Standard Scalers and robust scalers on datasets that have implemented the SMOTE method and without SMOTE to find algorithms and techniques with the highest accuracy and performance from the best algorithms using ROC curve values ​​and AUC values. In this study, researchers will use Logistic Regression, Random Forest, and Perceptron. Comparing the Standard Scaler and Robust Scaler methods as data standardization. And using the SMOTE technique and not using SMOTE to overcome unbalanced classes. As a result, the Random Forest algorithm with SMOTE technique and Standard Scaler is suitable for classifying and predicting heart failure.
Analisis dan Perancangan Sistem Informasi Kasir UMKM Berbasis Website Untuk Mengontrol Penerapan Manajemen Bisnis Lokesworo; Saruni Dwiasnati; Herfandi
Computer Science Research and Its Development Journal Vol. 14 No. 3: October 2022
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid.14.3.2022.287-301

Abstract

Micro, Small and Medium Enterprises (MSMEs) are increasingly experiencing development in Indonesia. The transaction data process that runs on the Rosereve Esthetic Brand MSMEs is still recorded on the general ledger. The Business process only produces data on sales of goods in raw form, making it difficult to make sales reports per day, weekly and monthly. A website-based cashier information system has been widely implemented to solve this. Therefore, this research will build a website-based cashier information system. This research resulted in a website-based cashier information system with a development method using Agile, Analysis and design using context diagrams and data flow diagrams. There are amount and profit per transaction features on the report page that can be viewed by period and have two users with different access rights. Testing with the black box testing method got the "Success" result. This research is expected to help management control the running Business processes.
Rancang Bangun Sistem Keamanan Pintu Rumah Menggunakan Arduino Berbasis Android Eko Setyo Budi Putra Aji; Rika Rosnelly
Computer Science Research and Its Development Journal Vol. 15 No. 1: February 2023
Publisher : LPPM Universitas Potensi Utama

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

Abstract

Many people still find it difficult to secure their doors with the current technological orientation. Many people look for safety devices for their doors on various websites, but they are still constrained by the price and how to install the equipment purchased on their door. The existence of tools and applications for designing a home door security system is made with the aim of helping people to secure their door in an easier and more efficient way. The design of the home door security system with the available Android-based Arduino makes it easier for people to secure their home doors, of course, with guides and understanding of the tools described by the author. Tools made using Arduino and applications are made using the Java programming language. The system development, method for making this application uses the MIT App Inventor.
Eksperimen Perbandingan Evolutionary Programming dan Evolutionary Strategies dalam Permasalahan Maximization Fungsi Polinomial Ahmad Nugroho; Maria Siregar
Computer Science Research and Its Development Journal Vol. 15 No. 3 (2023): October 2023
Publisher : LPPM Universitas Potensi Utama

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

Abstract

Evolutionary Programming and Evolutionary Strategies are two techniques in Evolutionary Computation. Both are relatively similar but in Evolutionary Strategies, crossover is not used and only mutation is performed using normally distributed noise. To determine which is better in solving the problem of maximizing a polynomial function, this study aims to compare both. Implementation will be made using the Python programming language with the DEAP (Distributed Evolutionary Algorithms in Python) library. Then both are run 100 times to find the average number of generations needed to achieve an accuracy of at least 1e-5. Based on the research, it was found that Evolutionary Strategies provides more efficient performance by 4%.

Page 1 of 5 | Total Record : 45

 1   2   3   4   5 

Filter by Year

2022 2024


Reset
Filter By Issues
All Issue Vol. 16 No. 2 (2024): June 2024 Vol. 16 No. 1 (2024): February 2024 Vol. 15 No. 3 (2023): October 2023 Vol. 15 No. 2: June 2023 Vol. 15 No. 1: February 2023 Vol. 14 No. 3: October 2022