cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Irfan Syamsuddin
Contact Email
jurnaljicer@poliupg.ac.id
Phone
+6281242117575
Journal Mail Official
jurnaljicer@poliupg.ac.id
Editorial Address
Jl. Tamalanrea raya (BTP) Moncongloe, Kampus 2 Politekik Negeri Ujung Pandang, Makassar
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Journal of Informatics and Computer Engineering Research
Published by Politeknik Negeri Ujung Pandang
ISSN : -     EISSN : 30896320     DOI : https://doi.org/10.31963
Core Subject : Science,
Computer Science & IT
Journal of Informatics and Computer Engineering Research PNUP is research journal as a forum for scientific communication between academics, researchers and practitioners in disseminating research results in the fields of Information System, Networking, Mobile Applications, Software Engineering, Web Programming Mobile Computing, Science Application, Virtual Reality, Multimedia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 15 Documents
 1   2 
KINERJA HYBRID MONGODB-ELASTICSEARCH PADA APLIKASI SOCIAL NETWORK ANALYSIS Jaury, Muhammad; Olivya, Meylanie; Nur, Rini
Journal of Informatics and Computer Engineering Research Vol. 1 No. 1 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i1.4916

Abstract

Social media data is growing rapidly in size, variety and complexity. Social media data stores various potential information such as sentiment analysis, trend predictions etc. Potential information can be extracted through Social Network Analysis. SNA has a major challenge which is to process very large datasets in a reasonable time. One of the efforts that can be done is create hybrid system of MongoDB and Elasticsearch using social media datasets from Twitter. The results of this study that the highest response time in insert process starting from 26.2s on 1K data to 19520.45s on 1M data. The replication process with 1K tweet data is 6.25s to 1M tweets is 2817,146s. The select process has under 0.1s and relatively constant due to the Inverted Index on Elasticsearch. Highest CPU performance in process of selecting data from Elasticsearch. Highest RAM performance in the insert process to MongoDB and data replication to Elasticsearch.
INOVASI SISTEM PEMERIKSAAN UJIAN SELEKSI CALON MAHASISWA BARU DI POLITEKNIK NEGERI UJUNG PANDANG Dzulmukmin, Andi Abdul; Tungadi, Eddy; Abduh , Ibrahim
Journal of Informatics and Computer Engineering Research Vol. 1 No. 1 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i1.4918

Abstract

The inspection system for the entrance exam to the state polytechnic in Ujung Pandang is a process for checking participant computer answer sheets (LJK) to obtain the scores of participants who took the exam so that it becomes a benchmark for participants' graduation of the desired study program. The previous UMPN inspection system had drawbacks, namely the program inspection system still needed to be developed in terms of accuracy and effectiveness. Designing an FSI inspection program that has high accuracy requires data collection such as FSI along with references to similar inspection programs. The LJK inspection program uses the python language with the image processing library, namely openCV. LJK will be scanned and produce 100dpi and 200dpi LJK images which will be tested in the FSI inspection program. Based on the program testing conducted, it is recommended to use a 15x15 pixel resolution of 100dpi with an average accuracy of 99.31% and for a 200dpi resolution it is recommended to use 30x30 pixels with an average accuracy of 99.98%.
PENGEMBANGAN SISTEM BIG DATA: RANCANG BANGUN INFRASTRUKTUR DENGAN FRAMEWORK HADOOP Sudirman , Ahmad; Irawan; Saharuna , Zawiyah
Journal of Informatics and Computer Engineering Research Vol. 1 No. 1 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i1.4919

Abstract

Hadoop is a distributed data storage platform that provides a parallel processing framework. HDFS (Hadoop Distributed File System) and Map Reduce are two very important parts of Hadoop, HDFS is a distributed storage system built on java, while Map Reduce is a program for managing large data in parallel and distributed. The research focused on testing the data transfer speed on HDFS, testing using 3 types of data, namely video, ISO Image, and text with a total of 512 MB, 1 GB, and 2 GB of data. Testing will be carried out by entering data into HDFS using the Hadoop command and changing the size of the block size with parameters 128 MB, 256 MB and 384 MB. Hadoop's performance on a large block size of 384 MB has better speed than block sizes of 128 MB and 256 MB because the data will be divided into 384 MB so that data mapping will be less than on block sizes of 128 MB and 256 MB.
PENERAPAN MACHINE LEARNING UNTUK MENGATASI KETIMPANGAN DATA DALAM MENENTUKAN KLASIFIKASI UANG KULIAH TUNGGAL (UKT) Syam, Nurul Tarizya; Irmawati; Saharuna , Zawiyah
Journal of Informatics and Computer Engineering Research Vol. 1 No. 1 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i1.4921

Abstract

Single Tuition Fee or UKT is a tuition fee borne by students every semester. Payment is made every time students enter a new semester while studying at tertiary institutions. One of the state universities in Indonesia that has implemented the UKT payment system is Politeknik Negeri Ujung Pandang. Based on observations, the purchase of UKT is still done manually, so it has the potential to produce decisions that are not on target. This study was classified based on the amount of single student tuition fees using the smote method and without smote. The algorithm used in classifying is SVM, Decision Tree, Random Forest. The data used is 985 UKT data in 2021. Based on experiments that have been carried out with the Random Forest algorithm, it has the best performance compared to the SVM and Decision Tree algorithms. The proportion of results obtained before being hit is accuracy of 84.75%, precision of 79.22%, recall of 81.15% and F1 score of 80.17%. Whereas after applying smote it increased with an accuracy proportion of 98.9%. So it can be interpreted that the best algorithm used in classification is the Random Forest algorithm by applying smote.
PENERAPAN TEKNOLOGI BLOCK STORAGE DALAM SISTEM VIRTUALISASI BERBASIS OPENSTACK Putri , Oka Karma; Irawan; Saharuna , Zawiyah
Journal of Informatics and Computer Engineering Research Vol. 1 No. 1 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i1.4922

Abstract

In agriculture, the drip irrigation system is still using a manual system, so it is necessary to develop an automatic irrigation system that can make it easier for farmers to control water supply. network The use of wireless sensors in agriculture is a field that is experiencing an increase. Using a wireless network helps farmers when they have to carry out cable maintenance and repairs in areas that are difficult to reach. This study aims to implement a wireless sensor network based on ESP8266 for drip irrigation system automation that monitors changes in soil moisture and plant temperature, as well as automatic drip irrigation control. The method used in this study is the Waterfall Method, this model develops systematically from one stage to the next. The maximum range distance that can be achieved by the router node to send data to the sink node is 140 meters at the Line Of Sight (LOS) position. At the same time, the router node also controls drip irrigation automatically by sending commands to the actuator node (drip controller) to open or close the solenoid valve connected to the water reservoir which will circulate air by gravity. To implement it, you need ESP8266, YL-
EVALUASI KINERJA LOAD BALANCING DENGAN ALGORITMA SCHEDULLING NEVER QUEUE Zulfianndari; Irmawati,; Nur , Rini
Journal of Informatics and Computer Engineering Research Vol. 1 No. 2 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i2.5176

Abstract

Load balancing is used as a technique to handle large loads that cannot be carried out by a single server, so that the server does not experience overload. In handling load sharing, Load balancing uses a scheduling algorithm (Scheduling). The scheduling algorithm that is generally used is Round Robin which works by dividing requests evenly and then creating a queue for the server so that unfinished processes wait in the queue for quite a long time. In the Load balancing system there is an algorithm that adopts two speed models, which works by looking at the server status and the smallest connection delay, namely the Never Queue Algorithm. This study aims to determine the performance of Load balancing when the Schedulling Never Queue Algorithm is applied, based on predetermined scenarios and parameters. This study succeeded in implementing the Never Queue Algorithm in a Load balancing system for the Apache web server where the Time Per Request value will be lower if the Request received is larger when compared to using the Round Robin Algorithm. The Request Per Second value increases when the Requests sent are getting bigger. In terms of sharing server connections, the load balancer will share the load on the number of Requests based on the Shortest Expected Delay (SED) Algorithm, so several web servers receive different numbers of connections, so that processes don't stay in queues for a long time.
ANALISIS POLA PENYAKIT DENGAN METODE ASSOCIATION RULE (STUDI KASUS : RSUD LABUANG BAJI) Mintu, Yupita Febriani; Yusri, Iin Karmila; Saharuna , Zawiyah
Journal of Informatics and Computer Engineering Research Vol. 1 No. 2 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i2.5177

Abstract

RSUD Labuang Baji has a lot of medical record data, but this medical record data has not been used optimally and has not been processed to produce useful information for Laburan Baji Hospital. In this study the data used were outpatient medical record data in 2019, by analyzing three attributes, namely disease diagnosis (ICD), gender, and age group. The method for conducting data analysis is the association rule method using the Apriori algorithm and Tools R. The results of this study are disease patterns using a minimum support value of 0.01 and a minimum confidence value of 0.6, and the disease pattern formed is an associative rule with a combination of 2k-itemset and 3k item set of 25 associative rules where the rules for this disease pattern have a lift ratio value of > 1, so this disease pattern can be used as a recommendation to improve hospital services.
PENERAPAN ALGORITMA OPPOSITION-BASED WHALE DALAM KLASIFIKASI SVM UNTUK ANALISIS SENTIMEN TERHADAP KEBIJAKAN PPKM Said, Asrul; Tungadi, Eddy; Olivya , Meylanie
Journal of Informatics and Computer Engineering Research Vol. 1 No. 2 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i2.5178

Abstract

Corona Virus Disease 2019 (COVID-19) has had a serious impact, forcing the Indonesian government to establish various policies to deal with the spread of COVID-19. One of these policies is the Implementation of Restricting Community Activities (PPKM). During its implementation, this policy raised pros and cons in the community, especially on Twitter social media. The existence of this public opinion, can be used as an effective source of information to assist the government in taking and evaluating policies. The purpose of this study was to determine public sentiment towards PPKM policies based on the classification of tweets or public opinion on Twitter. This process is carried out by applying the OBWOA method for selecting appropriate and optimal SVM parameters and feature selection to select the best features thereby reducing computation time and producing good classification performance. The results of the optimization of the SVM parameters obtained C = 4.99522643 and gamma = 1.4236435 with an average accuracy of 75.20%, precision of 79.73%, recall of 71.65%, and f measure of 70.88%. The feature selection results obtained an average accuracy of 82.40%, precision of 84.23%, recall of 79.63%, and f-measure of 78.96%. In addition, the sentiment classification of 1,389,481 public tweet data in the period January to December 2021 obtained 53% of tweets with Negative sentiment, 25% of Tweets with Neutral sentiment, and 22% of tweets with Positive sentiment.
IMPLEMENTASI DEEP LEARNING UNTUK PENDETEKSIAN PENGGUNA MASKER PADA CCTV: STUDI KASUS PUSKESMAS SUDIANG RAYA Trisnaningrun, Ainun; Tungadi, Eddy; Syamsuddin, Irfan
Journal of Informatics and Computer Engineering Research Vol. 1 No. 2 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i2.5184

Abstract

The use of mask is one of the things that needs attention when you want to leave the house to implement health protocols to avoid diseases that are currently troubling people in the world or commonly known as Covid-19. Currently, people are reluctant to come to the hospital for fear of being exposed to the Covid-19 virus, so people who need treatment prefer to visit the puskesmas near their home. However, there are still many people who do not use masks on the grounds that the intended location is close to home. To overcome this can be done by detecting visitors' faces using the camera. So a system is proposed, namely the detection of mask users with the Convolutional Neural Network (CNN) method. One of the widely applied CNN methods for processing image data is YOLO. YOLO (You Only Look Once) is a deep learning-based model developed to detect an object in real-time. YOLO works by looking at the image as a whole, then using a neural network and automatically detecting existing objects. So that in this study the YOLO model, namely YOLOv4, was used as an object detection model in a mask detection system with CCTV video media whose data is sent in real-time.
INOVASI APLIKASI ASESMEN NASIONAL MENGGUNAKAN TEKNOLOGI PROGRESSIVE WEB APP Muhamad Aslan, La Ode; Yusri, Iin Karmila; Raharjo , Muh. Fajri
Journal of Informatics and Computer Engineering Research Vol. 1 No. 2 (2024)
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/jicer.v1i2.5185

Abstract

The national assessment is a program for assessing the quality of each school, madrasah and equality program at the primary and secondary levels. The national assessment application utilizes network connectivity to send national assessment results data from the application to the server. However, the lack of equal distribution of network facilities and infrastructure is an obstacle in the use of national assessment applications. Therefore, to build a national assessment application system that can be accessed without having to depend on network connectivity, the system will be built using the Progressive Web App (PWA) concept. Meanwhile, by using the web app manifest, the website can bring up a pop-up add to homescreen which is useful for installing the system on the user's homescreen so that applications can be accessed quickly via the homescreen icon. By using indexedDB, even though in an offline state the user can still send data and the data will be saved to indexedDB and when the network returns online the data will be automatically synchronized with the server. From the results of testing the quality of PWA using Lighthouse, there is a decrease in the performance of the progressive web app application each time the number of users is added, this indicates that the number of users can affect the performance of a computer-based national assessment application using a progressive web app.

Page 1 of 2 | Total Record : 15

 1   2 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 2 No. 1 (2025) Vol. 1 No. 2 (2024) Vol. 1 No. 1 (2024)