cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ramdan Satra
Contact Email
Ramdan Satra
Phone
-
Journal Mail Official
ramdan@umi.ac.id
Editorial Address
-
Location
Kota makassar,
Sulawesi selatan
INDONESIA
ILKOM Jurnal Ilmiah
Published by Universitas Muslim Indonesia
ISSN : 20871716     EISSN : 25487779     DOI : -
Core Subject : Science,
Computer Science & IT
ILKOM Jurnal Ilmiah is an Indonesian scientific journal published by the Department of Information Technology, Faculty of Computer Science, Universitas Muslim Indonesia. ILKOM Jurnal Ilmiah covers all aspects of the latest outstanding research and developments in the field of Computer science, including Artificial intelligence, Computer architecture and engineering, Computer performance analysis, Computer graphics and visualization, Computer security and cryptography, Computational science, Computer networks, Concurrent, parallel and distributed systems, Databases, Human-computer interaction, Embedded system, and Software engineering.
Arjuna Subject : -
Articles 580 Documents
 46   47   48   49   50 
Comparative analysis of Fuzzy Tsukamoto's membership functions for determining irrigated rice field feasibility status Ummi Syafiqoh; Anton Yudhana; Sunardi Sunardi
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1156.255-263

Abstract

The representation of the fuzzy set membership curve consisting of trapezoidal, triangular, and linear shapes, has an important role in the fuzzy logic system. The selection of the curve's shapes determines the useable membership function and affects the fuzzy output value. Previous studies generally used curves that had been employed in predecessors or other studies that did not explain the reason for choosing a fuzzy member curve. This condition became problem because there was not a guide in selecting the appropriate membership function model for the parameters used in the fuzzy process so that most researchers only use membership functions that are commonly used in previous studies or in the same case as their research. The purpose of this study was to determine the effect of selecting trapezoidal and triangular curves on the performance of Tsukamoto's fuzzy logic for determining the rice-fields suitability status. The research methodology comprised 3 main stages. The first stage was data collecting, to collect soil pH values, soil moisture, and air temperature in rice fields. The second stage was the implementation of the Tsukamoto fuzzy. At this stage, two membership function curves were used. The third stage was a comparative analysis of Tsukamoto's fuzzy's output of trapezoidal and triangular curves. The results obtained indicate that there is no significant performance difference between the two different membership functions. The results of the research with the trapezoidal membership function have a better accuracy rate of 93% while the triangular membership function has an accuracy rate of 90%.
Classification of Lombok Pearls using GLCM Feature Extraction and Artificial Neural Networks (ANN) Muh Nasirudin Karim; Ricardus Anggi Pramunendar; Moch Arief Soeleman; Purwanto Purwanto; Bahtiar Imran
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1317.209-217

Abstract

This study used the second-order Gray Level Co-occurrence Matrix (GLCM) and pearl image classification using the Artificial Neural Network (ANN). No previous research combines the GLCM method with artificial neural networks in pearl image classification. The number of images used in this study is 360 images with three labels, including 120 A images, 120 AA images, and 120 AAA images. The epochs used in this study were 10, 20, 30, 40, 50, 60, 70, and 80. The test results at epoch 10 got 80.00% accuracy, epoch 20 got 90.00% accuracy, epoch 30 got 93.33% accuracy, and epoch 40 got 94.44% accuracy. In comparison, epoch 50 got 95.55% accuracy, epoch 60 got 96.66% accuracy, epoch 70 got 96.66% accuracy, and epoch 80 got 95.55% accuracy. The combination of the proposed methods can produce accuracy in classifying pearl images, such as the classification test results.
Identification of sea urchins in melonguane coastal area using Multilayer Perceptron Neural Network Andar Alwein Pinilas; Luther Alexander Latumakulita; Djoni Hatidja
ILKOM Jurnal Ilmiah Vol 14, No 2 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i2.1208.169-177

Abstract

Sea urchins (Echinoidea) are marine biota that is found in Indonesian waters and there are 950 types of sea urchins scattered throughout the world. This study aims to classify types of sea urchins based on the characteristics contained in sea urchin images using the Multilayer Perceptron Neural Network (MLP-NN) method with 3 classification classes. 120 sea urchin image data were taken from the Melonguane beach area, Talaud Islands Regency, North Sulawesi Province. In the MLP-NN stage, training, validation, and testing processes are carried out by applying 8-fold cross-validation, and the system performance shows the lowest accuracy of 93.33%, the highest 100%, and an average of 98.33%. The experimental results indicate that MLP-NN can classify sea urchins with good performance.
The development of Web-based information system using quick UDP internet connection Poetri Lestari Lokapitasari Belluano; Benny Leonard Enrico Panggabean; Purnawansyah Purnawansyah; Kasmira Kasmira
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1134.314-322

Abstract

The Academic Information System (xSIA) is built to its users to manage Study Program modules, including student academic grades. xSIA applying the Moodle Learning Management System (LMS) was developed by implementing Quick UDP Internet Connection (QUIC) technology with the HTTP/3 protocol which can demonstrate protocol transaction speed performance. The design of information systems and databases employs the Convention Over Configuration paradigm. The Prototyping Model is used to graphically represent the workflow of the system with an experimental research design. System modeling utilizes Unified Modeling Language (UML) tools, Data Base Management System (DBMS) using PostgreSQL, and UDP ports as a means of data communication. The implementation of Quick UDP Internet Connection (QUIC) on the xSIA moodle LMS is effective for real-time communications that do not require conditions to open, maintain, or terminate connections as in streaming video conference. It is also optimal because the UDP data is transferred individually and checked for its integrity upon arrival. When a video streaming transaction last 02:36 seconds with a file size of 4.1mb, there is a significant difference of 100.98ms in the waiting time to first byte (ttfb).
Analysis of recommendations for recipients of COVID-19 cash social assistance financing the ministry of social affairs Erliyan Redy Susanto; Rusliyawati Rusliyawati; Agus Wantoro; Citra Andini Purnama; Itce Diasari
ILKOM Jurnal Ilmiah Vol 14, No 2 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i2.1138.126-133

Abstract

In order to solve the problems that exist in the economic aspect due to the COVID-19 pandemic in Indonesia, the government has implemented various programs related to economic recovery. One of these programs is cash social assistance (BST). During the implementation of the social assistance program in various regions, it was reported that the recipients of the program were not properly targeted. Based on the results of a survey from one of the leading universities in Indonesia, it is known that many social assistance programs related to the impact of the COVID-19 pandemic are suspected to have not been in accordance with their designation. Based on this, the research was conducted in Bandar Lampung City. The purpose of this study is to conduct an analysis for recommendations for prospective BST recipients, namely people affected by Covid-19. The method used is profile matching by taking samples in the Jagabaya village, Bandar Lampung City. The criteria used include the work of the head of the family, wife's work, home status, number of dependents and ID cards. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City.
Generating game immersion features for immersive game selection Najirah Umar; Yuyun Yuyun; Hamdan Gani
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1224.264-274

Abstract

The immersion is an essential component of the modern digital game. Currently, immersion is the required component which should be included in the digital game. The modern game which success within game industry surely has included immersion as a component. Although digital games have been introduced for many years, yet what is immersion game been known very little. Regarding the intensive study about user immersion, there is still a lack of knowledge about game immersion. First, the game designers, game developers, and gamers are facing problems how to understand whether their game is immersive or not. There is no knowledge regarding how to evaluate their game, whether immersive or not, and this process requires expert knowledge. Second, currently, the game designers are relied on speculative interpretation to evaluate their game because there is no method to examine whether the game is immersive or not. Therefore, this study aims to propose a method  that enable to evaluate if the game is immersive or not. This method is emerged as knowledge and recommendation that quickly be able to assist the game designers, game developers, and gamers evaluating whether a game is immersive or not. First, this research conducts a literature review to categorize the game immersion features. Second, this study proposes an effective method that can analyse and recommends whether a game is immersive or not. Finally, this study reveals that the finding could be used as a recommendation for the other immersive technology platforms.
Classification of stroke patients using data mining with adaboost, decision tree and random forest models Bahtiar Imran; Erfan Wahyudi; Ahmad Subki; Salman Salman; Ahmad Yani
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1328.218-228

Abstract

A stroke is a fatal disease that usually occurs to the people over the age of 65. The treatment progress of the medical field is growing rapidly, especially with the technological advance, with the emergence of various medical record data sets that can be used in medical records to identify trends in these data sets using data mining. The purpose of this study was to propose a model to classify stroke survivors using data mining, by utilizing data from the kaggle sharing dataset. The models proposed in this study were AdaBoost, Decision Tree and Random Forest, evaluation results using Confusion Matrix and ROC Analysis. The results obtained were that the decision tree model was able to provide the best accuracy results compared to  the other models, which was 0.953 for Number of Folds 5 and 10. From the results of this study, the decision tree model was able to provide good classification results for stroke sufferers.
Deepfake Detection in Videos Using Long Short-Term Memory and CNN ResNext Muhammad Indra Abidin; Ingrid Nurtanio; Andani Achmad
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1254.178-185

Abstract

Deep-fake in videos is a video synthesis technique by changing the people’s face in the video with others’ face. Deep-fake technology in videos has been used to manipulate information, therefore it is necessary to detect deep-fakes in videos. This paper aimed to detect deep-fakes in videos using the ResNext Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) algorithms. The video data was divided into 4 types, namely video with 10 frames, 20 frames, 40 frames and 60 frames. Furthermore, face detection was used to crop the image to 100 x 100 pixels and then the pictures were processed using ResNext CNN and LSTM. The confusion matrix was employed to measure the performance of the ResNext CNN-LSTM algorithm. The indicators used were accuracy, precision, and recall. The results of data classification showed that the highest accuracy value was 90% for data with 40 and 60 frames. While data with 10 frames had the lowest accuracy with 52% only. ResNext CNN-LSTM was able to detect deep-fakes in videos well even though the size of the image was small.
Predicting the success of the government’s program of lomaya (Regional PKH) in reducing poverty Ruhmi Sulaehani; Marniyati Husain Botutihe
ILKOM Jurnal Ilmiah Vol 14, No 3 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i3.1149.323-328

Abstract

Poverty reduction is one indicator of the success of development. The form of support from the Pohuwato Regency Government through the Social Service is to organize PKH-D, which is known as LOMAYA. It is one of the implementations of the Community Movement Towards Independent Prosperity (Gerakan Masyarakat Menuju Sejahtera Mandiri). This research was conducted to assist the government in predicting the level of development success indicated by the satisfaction of beneficiaries of lomaya. The method employed was the Naïve Bayes method and forward feature selection. The research data was obtained from a survey of lomaya beneficiaries in the last two years. The accuracy result obtained using the Naïve Bayes algorithm was 94.19%, while Naïve Bayes with the Forward Selection feature was only 94.03%. Therefore, the Naïve Bayes algorithm method is better than the Forward Selection based Naïve Bayes algorithm. Forward selection does not improve accuracy because the selection process causes many attributes to be discarded because they are considered irrelevant. This happened because of the inaccuracy of the data after being selected for its attributes using the Forward Selection feature resulting 1 attribute  only as a determinant.
Comparative Analysis to Determine the Best Accuracy of Classification Methods Warnia Nengsih; Yuli Fitrisia; Mardhiah Fadhli
ILKOM Jurnal Ilmiah Vol 14, No 2 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i2.1128.134-141

Abstract

The classification method is one of the methods of supervised learning and predictive learning. This method can be used to detect an object in the image presented, whether it is in accordance with the existing object in the training phase. There are several classification methods used, including Support Vector Machine (SVM), K-Nearest Neighbors (K-NN) and Decision Tree. To determine the accuracy in detecting these objects, it is necessary to measure the accuracy of each classification method used. The object that becomes simulation in this research is the object image of Guava and Pear fruit. Testing using confusion matrix. The results showed that the Support Vector Machine (SVM) method was able to detect with an accuracy of 98.09%. Then the K-Nearest Neighbors (K-NN) method with an accuracy of 98.06%, then the Decision Tree method with an accuracy of 97.57%. From the results of the accuracy test, it can be concluded that basically these three classification methods have good accuracy with a difference of 0.49% and the overall average accuracy of the classification of the three methods is 97.89%

Page 48 of 58 | Total Record : 580

 46   47   48   49   50 

Filter by Year

2016 2025


Reset
Filter By Issues
All Issue Vol 17, No 3 (2025) Vol 16, No 3 (2024) Vol 16, No 2 (2024) Vol 16, No 1 (2024) Vol 15, No 3 (2023) Vol 15, No 2 (2023) Vol 15, No 1 (2023) Vol 14, No 3 (2022) Vol 14, No 2 (2022) Vol 14, No 1 (2022) Vol 13, No 3 (2021) Vol 13, No 2 (2021) Vol 13, No 1 (2021) Vol 12, No 3 (2020) Vol 12, No 2 (2020) Vol 12, No 1 (2020) Vol 11, No 3 (2019) Vol 11, No 2 (2019) Vol 11, No 1 (2019) Vol 11, No 1 (2019) Vol 10, No 3 (2018) Vol 10, No 3 (2018) Vol 10, No 2 (2018) Vol 10, No 2 (2018) Vol 10, No 1 (2018) Vol 10, No 1 (2018) Vol 9, No 3 (2017) Vol 9, No 3 (2017) Vol 9, No 2 (2017) Vol 9, No 2 (2017) Vol 9, No 1 (2017) Vol 9, No 1 (2017) Vol 8, No 3 (2016) Vol 8, No 3 (2016) Vol 8, No 2 (2016) Vol 8, No 2 (2016) Vol 8, No 1 (2016) Vol 8, No 1 (2016) More Issue