ILKOM Jurnal Ilmiah
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.
Articles
580 Documents
<![CDATA[Sentiment analysis of customer satisfaction levels on smartphone products using Ensemble Learning ]]>
<![CDATA[Muhammad Ma’ruf]]>;
<![CDATA[Adam Prayogo Kuncoro]]>;
<![CDATA[Pungkas Subarkah]]>;
<![CDATA[Faridatun Nida]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1377.339-347
<![CDATA[Increasingly sophisticated technological developments create new ways for people to conduct trading business. An example of this technology application is the use of e-commerce. However, there are conditions where the seller cannot measure the level of satisfaction and identify problems experienced by his customers if it is only based on the rating as the case in smartphones transactions. Therefore, a solution is needed to create a system that can filter negative and positive comments. This study offers a solution to address this issue by using machine learning employing the K-Nearest Neighbors, SVM, and Naive Bayes algorithms with hyperparameters from previous studies. This study applied the ensemble learning method with the Voting Classifier technique, which is an algorithm to combine several algorithms that have been made. From the test results, the highest accuracy was obtained by SVM with an accuracy value of 91.18% while the ensemble learning method obtained an accuracy value of 89.22%. The difference in the accuracy of training and testing for SVM and ensemble learning method is 7.1% and 4% respectively. These results indicate that the ensemble learning method can help improve the performance of sentiment analysis algorithms for comments on smartphone products.]]>
<![CDATA[Ripeness identification of chayote fruits using HSI and LBP feature extraction with KNN classification ]]>
<![CDATA[Siska Anraeni]]>;
<![CDATA[Erika Riski Melani]]>;
<![CDATA[Herman Herman]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 2 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i2.1153.150-159
<![CDATA[This study aims to build a system to identify the ripeness level of chayote that can be done easily and without damaging the quality of the chayote. This study employs digital image processing technology using Hue Saturation Intensity color feature extraction and texture feature extraction of Local Binary Pattern with K-Nearest Neighbor classification so that the process of identifying the ripeness level of chayote will be easier and more effective. This study uses 100 image datasets and is carried out by taking photos of chayote. The stages in this study include the input of chayote images followed by the image pre-processing stage. Next is feature extraction which is divided into three scenarios, namely HSI feature extraction, LBP feature extraction and a combination of the two feature extractions. The final stage is to classify objects that are closest to the object being tested using the KNN method. By determining the value of K in the KNN classification method, the results show that the use of the Chebyshev distance calculation model in LBP feature extraction with K = 5 is a test that has the best accuracy of 90%.]]>
<![CDATA[Information technology governance in University of Muhammadiyah Palembang using framework COBIT 5 domain; Evaluate, Direct and Monitor (EDM) ]]>
<![CDATA[Zulhipni Reno Saputra Elsi]]>;
<![CDATA[Karnadi Karnadi]]>;
<![CDATA[Jimmie Jimmie]]>;
<![CDATA[Fajrie Agus Dwino Putra]]>;
<![CDATA[Hartini Hartini]]>;
<![CDATA[Sri Primaini Agustanti]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1136.294-302
<![CDATA[This study aims to find out about Information Technology management at Muhammadiyah University of Palembang and to get right advice in managing Information Technology from the University level to the Study Program. Regarding benchmarks in Information Technology Governance use the Cobit 5 framework with the Evaluate, Direct and Monitor domains. Monitoring and evaluation was carried out using a questionnaire distributed to lecturers and employees at the Muhammadiyah University of Palembang and the researchers did observations on the management of higher education information technology governance. Based on the questionnaire result, the highest gap occurs in sub domain 4, which is 3.65 while the observation result towards the capability level is at level 3 with a value of 56.67%, the sub domain ensuring resource optimization has the highest capability value of 66.67%. Based on the data obtained using the EDM domain, the University of Muhamadiyah Palembang has to set Standard Operating Procedures (SOP) and Work Instructions (IK) so every five processes can run well to create good IT governance.]]>
<![CDATA[Extreme learning machine with feature extraction using GLCM for phosphorus deficiency identification of cocoa plants ]]>
<![CDATA[Basri Basri]]>;
<![CDATA[Muhammad Assidiq]]>;
<![CDATA[Harli A. Karim]]>;
<![CDATA[Andi Nuraisyah]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 2 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i2.1226.112-119
<![CDATA[This study aims to analyze the implementation of the Extreme Learning Machine (ELM) Algorithm with Gray Level Co-Occurrence Matrix (GLCM) as an Image Feature Extraction method in identifying phosphorus deficiency in cocoa plants based on leaf characteristics. Characteristic images of cocoa leaves were placed under normal conditions and phosphorus deficiency, each with 250 datasets. The feature extraction process by GLCM was analyzed using the ELM parameter approach in the form of Network Node_Hidden variations and several Activation Functions. The method of this case study was conducted with data collection, algorithm development to validation, and measurement using ROC. It was found that the best accuracy when testing the dataset was 95.14% on the node_hidden 50 networks using the Multiquadric Activation Function. These results indicate that the feature extraction model with GLCM using Contrast, Correlation, Angular Second Moment, and Inverse Difference Momentum properties can be maximized on Multiquadric Activation Function.]]>
<![CDATA[Factor analysis satisfaction levels of users toward the JKN mobile application in the COVID-19 Era using the PIECES framework ]]>
<![CDATA[Randa Gustiawan]]>;
<![CDATA[Ulung Pribadi]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1280.245-254
<![CDATA[This study aimed to prove the researcher's hypothesis regarding users’ factor analysis satisfaction of the Mobile JKN application in the Covid-19 era in Sungai Penuh City using the PIECES framework. The measurement variables of the PIECES framework were performance, information, economy, control, efficiency, and service. In this study, researchers used quantitative descriptive methods with data sources from questionnaires via google form with 101 respondents, and data processing was carried out using SEM-pls. The results of this study indicated the value of R square was 0.732. It can be concluded that the interpretation of the users’ satisfaction level of the application was 73.2%, which R-square identifies in the Strong/Good category. Several PIECES variables that has a significant effect on people's satisfaction with the JKN mobile application were efficiency and performance variables with P values of 0.004 and 0.033 while variables that did not have significant effect were control, economy, information and services.]]>
<![CDATA[Classification of Dog and Cat Images using the CNN Method ]]>
<![CDATA[Teguh Adriyanto]]>;
<![CDATA[risky aswi ramadhani]]>;
<![CDATA[Risa Helilintar]]>;
<![CDATA[Aidina Ristyawan]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1116.203-208
<![CDATA[Blind people can be defined as those people who are unable to see objects or pictures around them with their eyes. This inability becomes an issue for them when dealing with objects or images in front of them. These problems lead to the novelty of this study that is to recognize objects or images around blind people with the CNN algorithm. Dogs and cats were used as objects in this study. These object recognitions used Deep Learning, a relatively new science in the field of machine learning. Deep learning works like the human brain's ability to recognize an object. In this study, the objects that were used were pictures of a dog and a cat. This study used 3 types of data, namely training, validation, and testing data. The data training consisted of dog data with a total of 1000 images and cat data with a total of 1000 images. Data validation consisted of 500 dog data and 500 cat data. The CCN architecture employed 3 convolution layers. The layer was convolution 1 using 16 filters of kernel size 3x3, the second convolution using 32 filters of kernel size 3x3 and the third using 64 filters of kernel size 3x3. While the data testing consisted of 51dog data and 27 cat data. The method used to analyze the image was CNN. The input was an image with a size of 150x150 pixels with 3 channels, namely R, G, and B. This classification went through a performance test with the Confusion Matrix and it obtained 45% precision, 45% recall and 45% f1-score. From these results it can be concluded that the accuracy values should be improved.]]>
<![CDATA[Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN ]]>
<![CDATA[Herlina Jayadianti]]>;
<![CDATA[Wilis Kaswidjanti]]>;
<![CDATA[Agung Tri Utomo]]>;
<![CDATA[Shoffan Saifullah]]>;
<![CDATA[Felix Andika Dwiyanto]]>;
<![CDATA[Rafal Drezewski]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1505.348-354
<![CDATA[Reviews are a form of user experience information on a product or service that can be used as a reference for potential consumers’ preferences to buy, use, or consume a product. They can be also used by business entities to find out public opinion about their product or the performance of their business products. It will be very difficult to process the review data manually and it will take a long time. Therefore, sentiment analysis automation can be used to get polarity information from existing reviews. In this study, IndoBERT with Recurrent Convolutional Neural Network (RCNN) was used to automate sentiment analysis of Indonesian reviews. The data used was a sentiment analysis dataset obtained from IndoNLU with sentiment consisting of negative sentiment, neutral sentiment, and positive sentiment. The results of the test showed that IndoBERT with the Recurrent Convolutional Neural Network (RCNN) had better results than the IndoBERT base. IndoBERT with Recurrent Convolutional Neural Network (RCNN) obtained 95.16% accuracy, 94.05% precision, 92.74% recall and 93.27% f1 score.]]>
<![CDATA[Analysis of public opinion on COVID-19 vaccine through social media using Naïve Bayes theory algorithm ]]>
<![CDATA[Aishiyah Saputri Laswi]]>;
<![CDATA[Munir Yusuf]]>;
<![CDATA[Ulvah Ulvah]]>;
<![CDATA[Bungawati Bungawati]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 2 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i2.1127.160-168
<![CDATA[This study aims to analyze various public opinion on the Covid-19 vaccines that appear on social media pages, especially on Facebook and Twitter via # (hastag). The death rate caused by COVID-19 was so high which reached 144,227 people until 2022. The Indonesian government required vaccines for the community starting from children aged 6 years as an effort to prevent the spread of the Covid-19 virus. Unfortunately, the implementation of complete vaccines in Indonesia has only reached 51.3% of the mandatory vaccine population, which is 140 million out of 339 million people. The non-achievement of the target set by the government causes the need to conduct a sentiment analysis on vaccines in Indonesia through social media. Based on the sample data, from 1000 words obtained from 320 opinions there are positive and negative opinions. This data is then analyzed and processed to find out how many positive and negative responses occurred. The data was then processed into several stages to test the level of truth through training data and test data. The results of the data processing were tested using the Naïve Bayes algorithm which resulted in an accuracy value with a precession of 77.08% taken from 90 samples test data, recall with a percentage of 97.87% based on positive data which was predicted to be true with a positive opinion status from 47 samples of test data and 1 positive data status which is still predicted to be negative. Furthermore, the specific percentage value obtained was 65.30% of the 132 test data that are predicted to be true negative.]]>
<![CDATA[Multiplayer mechanism design for soil tillage serious game ]]>
<![CDATA[Anang Kukuh Adisusilo]]>;
<![CDATA[Emmy Wahyuningtyas]]>;
<![CDATA[Nia Saurina]]>;
<![CDATA[Radi Radi]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 3 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i3.1432.303-313
<![CDATA[The primary goal of Serious Games is not only for fun but also for lesson. In learning the first stage of soil tillage which using the mouldboard plow, a proper understanding is needed so that the soil tillage process will follow the needs of plant growth. The use of serious games as a study instrument for soil tillage is under the concept of digital game-based learning (DGBL). The problem of players when playing serious games is less motivated to play because the serious game system and scenario are less challenging. That challenges accelerate the shape of knowledge and experience when playing the games (user experience). By referring to the Learning Mechanics Gaming Mechanics (LM-GM) model, which is based on multiplayer in serious games, hopefully the learning process of land management using the mouldboard plow can be optimized. This process can increase learning motivation and elevate the user experience. This research results a design concept of a learning mechanism and a game mechanism for a serious multiplayer game of soil tillage with a mouldboard plow. There are three types of learning mechanisms in conceptual and concrete components, also six types of game mechanisms that can be used as a reference for the formation of multiplayer serious games and the increase player motivation.]]>
<![CDATA[Comparison of correlated algorithm accuracy Naive Bayes Classifier and Naive Bayes Classifier for heart failure classification ]]>
<![CDATA[Pungkas Subarkah]]>;
<![CDATA[Wenti Risma Damayanti]]>;
<![CDATA[Reza Aditya Permana]]>
<![CDATA[ ILKOM Jurnal Ilmiah Vol 14, No 2 (2022) ]]>
Publisher : <![CDATA[Prodi Teknik Informatika FIK Universitas Muslim Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v14i2.1148.120-125
<![CDATA[Heart failure (ARF) is a health problem that has relatively high mortality and morbidity rates in developed or developing countries, including Indonesia. In 2016, WHO stated that 17.5 million people died from cardiovascular disease, while in 2008, HF disease represented 31% of patient deaths worldwide. One of the new breakthroughs for early diagnosis is utilizing data mining techniques. In this study, the Correlated Naive Bayes Classifier (C-NBC) and Naive Bayes Classifier (NBC) algorithms are used to obtaining the best accuracy results so that they can be used for the Heart Failure dataset. Based on the results of the tests that have been carried out, it shows that the Correlated Naive Bayes Classifier (C-NBC) algorithm accuracy of 80.6% obtains higher accuracy than the Naive Bayes Classifier (NBC) algorithm of 67.5%. With the results of this study, the use of the Correlated Naive Bayes Classifier (C-NBC) algorithm can be used to diagnose patients with heart failure (heart failure) because it has a high level of accuracy and is categorized as Good Classification.]]>
