cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dr. Dian Palupi Rini
Contact Email
dprini@unsri.ac.id
Phone
-
Journal Mail Official
sjia@unsri.ac.id
Editorial Address
Fakultas Ilmu Komputer UNSRI
Location
Kab. ogan ilir,
Sumatera selatan
INDONESIA
Sriwijaya Journal of Informatics and Applications
Published by Universitas Sriwijaya
ISSN : -     EISSN : 28072391     DOI : -
Core Subject :
Sriwijaya Journal of Informatics and Applcations (SJIA) is a scientific periodical researchs articles of the Informatics Departement Universitas Sriwijaya. This Journal is an open access journal for scientists and engineers in informatics and Applcations area that provides online publication (two times a year). SJIA offers a good opportunity for academics and industry professionals to publish high quality and refereed papers in various areas of Informatics e.q., Machine Learning & Soft Computing, Data Mining & Big Data Analytics, Computer Vision and Pattern Recognition and Automated Reasoning, and Distributed and security System
Arjuna Subject : -
Articles 49 Documents
 1   2   3   4   5 
Bully Comments Classification on TikTok Using Support Vector Machine and Chi-Square Feature Selection Putri, Amelia; Abdiansyah, Abdiansyah; Utami, Alvi Syahrini
Sriwijaya Journal of Informatics and Applications Vol 5, No 1 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i1.71

Abstract

TikTok has been named the world’s most popular social media platform. The high level of TikTok use makes it easier for an irresponsible user to do unethical things such as spreading hateful comments on someone’s account. TikTok developers can prevent bullying by using policies such as word detection and filtering features that indicate comments fall under the category of bullying or non-bullying comments. Therefore, we conducted this study to classify bullying comments using Machine Learning methods for convenience purposes on TikTok usage, a method that we used in this research is the SVM method to classify the data and Chi-Square as the feature selection. Tests were carried out using the Linear, Polynomial, and RBF kernel functions with the C parameter, namely 0,1, 1, and 10 for each kernel. The results of this research show that the Support Vector Machine method with Chi-Square Feature Selection has a better performance.  This was proven by the increased accuracy in RBF kernel C=0,1 which was 0,20
Decision Support System For New Employee Selection Using AHP And TOPSIS Fahriza, Dicky; Abdiansyah, Abdiansyah; Rodiah, Desty
Sriwijaya Journal of Informatics and Applications Vol 5, No 1 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i1.67

Abstract

There are so many prospective workers with the same educational background, but not necessarily in accordance with the required company position and not necessarily they have the same expertise. To minimize the occurrence of errors, it can be done by making a decision-making system (DSS) to provide these recommendations. In this study, the Analytical Hierarchy Process (AHP) and the Technique For Order Preference by Similarity to Ideal Solution (TOPSIS) method were used to provide recommendations for prospective new employees. The steps taken are to compare the importance of each criterion weight with the AHP method. Then the ranking stage is carried out using the TOPSIS method to get recommendations for selected employees. The data used in this study is primary data in the form of 70 data on prospective employees from PT Hutama Jaya Perkasa. From the 70 data then selected to be 36 prospective employees based on the order of the highest ranking. Software testing is done by comparing the results of system calculations and the results of company calculations. Based on the test results obtained an accuracy value of 94.4%.
Generating Indonesian Poem: A Fine-Tunning Approach Using Pretrained GPT-2 Models Kusuma, Arya Mulya; Abdiansah, Abdiansah
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.96

Abstract

In recent years, text generation has become an important subfield within Natural Language Processing (NLP), gaining significant attention and focus. Over the past decade, text generation technology has expanded significantly, reaching diverse application domains, especially in creative areas such as poem. Generating poetic content is a unique challenge that requires combining linguistic knowledge, creativity, and originality to craft each poem. This study focuses on developing a text generator for Indonesian language poem, using fine-tuning methodology with the pre-trained GPT-2 model from the Flax community. The study conducted a comparative analysis, benchmarking the performance of the researcher's model against a baseline model developed by Muhammad Agung Hambali. The evaluation outcomes showed the researcher's model outperformed the baseline model, exhibiting a 73.68% improvement in perplexity value. Furthermore, the study conducted a survey involving 62 respondents to determine the reception of the generated poem. The results indicated the poem produced by the research model was marginally superior to that of the baseline model. 
Predictive Modeling of Air Quality Index Using Ensemble Learning and Multivariate Analysis Primanita, Anggina; Satria, Hadipurnawan
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.121

Abstract

Breathing polluted air can result in multiple health problems. Thus, it is important to understand and predict the air quality in the environment. Air Quality Index (AQI) is a unit used to measure the air pollutants. In Indonesia, this value is measured and published by the Meteorological, Climatological, and Geophysical Agency regularly. In this research, four commonly used regression algorithms were used to analyzed AQI data, namely, Random Forest, Decision Tree, K-Neural Network, and Ada Boost. All the algorithms model were developed to analyzed 1096 AQI data. The Mean Squared Error value of each model was computed as a measure of comparison. It is found that the Random Forest is the best performing algorithm. It can generalize well without overfitting to the data set.
Securing and Concealing Messages in the Edge Area of Digital Images Using Least Significant Bit Method and Blowfish Algorithm Nur, Arviansyah; Supardi, Julian; Rachmatullah, M. Naufal
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.88

Abstract

The process of cryptography produces random text that can obscure a message, making it difficult for others to read. However, cryptography itself is still not strong enough to secure the message, so steganography is needed to conceal the existence of the message from the human eye. Besides hiding the message, another objective is to assess the impact of message embedding. In the process of encrypting and decrypting the message, the Blowfish algorithm is used, while message embedding utilizes the Least Significant Bit steganography, and edge detection is performed using the Canny algorithm. Through research conducted with the combination of cryptography and steganography, an excellent image is obtained with a PSNR value of 76.6932 and MSE of 0.0013 for a message length of 64 bytes. Meanwhile, visually, the results show a relatively similar appearance between the host image and the stego image.
Fisheries Harvest Prediction using Genetic Algorithm Optimized of Gated Recurrent Unit Herman, Adelwin; Utami, Alvi Syahrini; Darmawahyuni, Annisa
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.109

Abstract

Indonesia is a maritime country with most of the population living near water areas. Water products are a common commodity often consumed cheaply, and food is therefore one of the primary human needs. Fishery harvest predictions are needed to control prices, prepare seeds, and ensure stable sales and consumption. The reason for choosing GRU for this prediction is that classical methods, commonly used in econometrics or time series analysis, were previously prevalent. GRU requires fewer operations than LSTM. Instead of training with an optimization algorithm relying on backpropagation and gradients, metaheuristic optimization in the form of a GA is used. GA does not require gradient information and is expected to avoid local optima. The total average MSE obtained is 9.55%.
Diagnosing Disease Of Betta Fish Using Fuzzy Logic Sugeno And Forward Chaining Method Pratama, M Wahyu; Utami, Alvi Syahrini; Kurniati, Rizki
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.87

Abstract

Betta fish are very popular with people of all ages who make betta fish as small and medium businesses who consider betta fish as a business, but betta fish maintenance is quite the opposite. The ease of breeding betta fish and ignorance in caring for good fish can cause death in betta fish caused by various diseases. Therefore, an expert system for diagnosing disease in betta fish was created. In this study the Forward Chaining method was used to diagnose fish disease, while the Fuzzy Sugeno method determined the severity of the disease. The accuracy generated by the system based on tests carried out using 100 data was 93%.
Optimization of Tsukamoto FIS Using Genetic Algorithm for Rainfall Prediction in Banyuasin Regency Akbar, Muhammad Rafi; Miraswan, Kanda Januar; Rodiah, Desty; Buchari, Muhammad Ali; Marjusalinah, Anna Dwi
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.118

Abstract

Indonesia, as a tropical country with high rainfall, heavily relies on accurate rainfall predictions for various critical purposes, including water resource management and extreme weather impact mitigation. One commonly used method is the Tsukamoto Fuzzy Inference System (FIS). However, implementing the Tsukamoto FIS often leads to high error rates. This is attributed to the difficulty in determining the boundaries of fuzzy variable membership functions. To address this issue, this research proposes an innovative approach by optimizing the boundaries of fuzzy membership functions using Genetic Algorithms (GA). The study resulted in a 49.02% reduction in the error rate, decreasing from 76.82% to 27.8%. This method significantly enhances rainfall prediction accuracy and contributes to the advancement of more sophisticated prediction methods. The optimization method proposed in this study also holds potential for application across various atmospheric science contexts.
Subject scheduling system using Ant Colony Optimization at MAN 3 Palembang Al Ashri, Muhammad Rizky; Miraswan, Kanda Januar; Darmawahyuni, Annisa; Utari, Meylani
Sriwijaya Journal of Informatics and Applications Vol 5, No 2 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i2.119

Abstract

In preparing the subject schedule, it must be done correctly because all teaching and learning activities are between teachers and students. So far, the subject scheduling process at MAN 3 Palembang is carried out manually so that clashes often occur between subjects and teachers who teach can teach in different classes at the same time resulting in the teaching and learning process being slightly disrupted. One of the common metaheuristic algorithms The solution used for optimization problems is the Ant Colony Optimization algorithm or commonly known as the ant algorithm. The application system or users of this application to create schedules using the Ant Colony Optimization algorithm method is useful for operators who create schedules in schools. This system can also be applied in cases where schedules conflict, namely teachers teaching in the same room and teachers teaching the same subject teaching in different classes at the same hours. This makes it easier for operators to create schedules so that they can be resolved more easily and quickly. This application was successfully developed into a subject scheduling system and managed to run optimally. From the results of implementing scheduling using the Ant Colony Optimization algorithm method used in compiling subject rosters, it can help the MAN 3 Palembang school which previously carried out schedule preparation manually.

Page 5 of 5 | Total Record : 49

 1   2   3   4   5 

Filter by Year

2020 2024


Reset
Filter By Issues
All Issue Vol 5, No 2 (2024) Vol 5, No 1 (2024) Vol 4, No 2 (2023) Vol 4, No 1 (2023) Vol 3, No 2 (2022) Vol 3, No 1 (2022) Vol 2, No 2 (2021) Vol 2, No 1 (2021) Vol 1, No 1 (2020)