The Indonesian Journal of Computer Science
The Indonesian Journal of Computer Science (IJCS) is a bimonthly peer-reviewed journal published by AI Society and STMIK Indonesia. IJCS editions will be published at the end of February, April, June, August, October and December. The scope of IJCS includes general computer science, information system, information technology, artificial intelligence, big data, industrial revolution 4.0, and general engineering. The articles will be published in English and Bahasa Indonesia.
Articles
1,127 Documents
<![CDATA[Assessment on Water Resource Management for Sedawgyi Dam: A WEAP Analysis Approach ]]>
<![CDATA[Htoo, Thet Zin]]>;
<![CDATA[Yin Yin Htwe]]>;
<![CDATA[Cho Cho Thin Kyi]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i5.4272
<![CDATA[This study employs the Water Evaluation and Planning (WEAP) system to analyze water resource management for the Sedawgyi Dam in Myanmar. The research integrates hydrological data, demand projections, and infrastructure information to simulate current and future water scenarios. Key steps include model setup, calibration, scenario development, and analysis. The results indicate that Mandalay City's highest domestic water demands are in Chanmyatharzi and Aungmyaetharzan townships, with agricultural water demands peaking in Mattaya township. The reference scenario highlights a significant domestic water supply shortfall, meeting only 10% of the demand, while agricultural demands are nearly fully met. The study underscores the urgent need for improved water management strategies to address rising unmet water demands, particularly for domestic use, to ensure sustainable water resource allocation in the region.]]>
<![CDATA[Evaluation of Stream Flow and Water Demand due to Climate Change in the Katha Basin Using Water Evaluation and Planning (WEAP) Model ]]>
<![CDATA[Tun, Win Lwin]]>;
<![CDATA[Cho Cho Thin Kyi]]>;
<![CDATA[Yin Yin Htwe]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i5.4273
<![CDATA[This study addresses the critical issue of assessing climate change impacts on streamflow and water demand in the Katha basin using the WEAP hydrological simulation model with the Soil Moisture (SM) method. The Katha basin, situated within Ayeyarwaddy River basin, faces variability in stream flow due to changing climatic conditions, impacting water availability for agriculture and domestic use. Through WEAP modeling, calibrated and validated against observed data from 2000-2012, the study projects an increase in annual flows under future scenarios (SSP245 and SSP585). Results indicate potential decreases in monsoonal flows, affecting water availability for agriculture and domestic use, necessitating adaptive management strategies. Model performance assessed by Nash Sutcliffe Efficiency (NSE) and Coefficient of Determination (R2) shows satisfactory agreement with observed data. The study underscores the urgency of integrated water resource management to sustainably address water demands amid climate variability, highlighting implications for agricultural productivity and water security in the region.]]>
<![CDATA[Perbandingan Random Search dan Algoritma Genetika dalam Penyetelan Hyperparameter XGBoost pada Retail Sales Forecasting ]]>
<![CDATA[Tiastama, Sheren Afryan]]>;
<![CDATA[Budi, Indra]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4285
<![CDATA[Sales is part of the important factor that influences a company in determining two things, namely profits and losses on the company. The right strategy to determine the amount of sales can be done through forecasting. Therefore, sales forecasting requires the right technique to produce accurate results. Machine learning has been proven to help overcome sales forecasting, one of which is XGBoost. However, XGBoost has many hyperparameters that affect its performance, it requires a hyperparameter setting method to produce an optimal hyperparameter. Random searches and genetic algorithms are optimized methods to find the optimal hyperparameter on XGBoost. The two methods of optimization were compared in this study with the measurement of RMSE performance in doing retail sales forecasting on the sales data of the retail company Rossmann Store which comes from the Kaggle site. The research obtained random search results superior to the genetic algorithm with RMSE values on the training process and the testing process are 0.123 and 0.122. Meanwhile, the RMSE values generated by genetic algorithms in the training and testing process are 0.333 and 0.332.]]>
<![CDATA[Penentuan Kriteria Vendor Teknologi Informasi Strategis Menggunakan Metode Fuzzy Analytical Hierarchy Process: Studi Kasus PT ABC ]]>
<![CDATA[Ardyani, Silvia Ayu]]>;
<![CDATA[Shihab, Muhammad Rifki]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i5.4288
<![CDATA[PT ABC is a national scale financial company whose services have spread throughout Indonesia and several countries in the world. Apart from that, PT ABC also encourages digitalization in improving its digital services. In improving its digital services, PT ABC involves all internal resources and IT vendors. During 2023, there will be 189 IT vendors collaborating with PT ABC. With a large number of IT vendors, it is necessary to group IT vendors to make it easier for companies to determine future strategies. Currently it is felt that determining the criteria for strategic IT vendors is no longer appropriate to the company’s conditions, so updated are needed. Determination of the criteria and subcriteria for this research was carried out through focus group discussion with 3 respondents. The results of the FGD stated 3 criteria and 2 subcriteria that could be used in this research. These criteria and subcriteria were then weighted using the fuzzy analytical hierarchy process (FAHP) method which was then tested on 25 IT vendors randomly.]]>
<![CDATA[Project Management Maturity Level and PMBOK 7th Recommendations: Case Study of an IT Service Provider Company ]]>
<![CDATA[Egie, Maria Clara]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4290
<![CDATA[As a provider of consulting and solutions in the ICT field, PT XYZ has the responsibility to complete projects within budget, on time, and meeting all specified scopes. However, projects from 2022-2023 have experienced delays in completion ranging from 1-6 months from the initial planning. This has resulted in the projects being considered unsuccessful due to these delays. Based on the analysis, there is a need to analyze the project management maturity level in PT XYZ's CRM division. This research aims to measure the project management maturity level and provide recommendations to improve it to the desired level. The maturity level measurement will use the Kerzner Project Management Maturity Model (KPM3). Through the measurement results, it was found that PT XYZ's CRM division has not yet passed the first level. Recommendations have been provided based on KPM3 to progress to the next level. Knowledge area-specific recommendations have also been given based on the 7th edition of PMBOK.]]>
<![CDATA[Application of Fuzzy Logic Mamdani in IoT-Based Air Quality Monitoring Systems ]]>
<![CDATA[Richi Andrianto]]>;
<![CDATA[Nopi Purnomo]]>;
<![CDATA[Yuda Irawan]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 5 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i5.4291
<![CDATA[This study aims to develop and implement an air quality monitoring system using Internet of Things (IoT) technology and Mamdani fuzzy logic. The system integrates sensors to detect PM2.5, PM10, and CO concentrations. Real-time data is processed using fuzzy logic to generate an easily understandable Indeks Standar Pencemar Udara (ISPU). Testing showed 95% accuracy in ISPU measurement, 2-second response time, and 99.5% uptime over 30 days. The Mamdani fuzzy logic effectively handles uncertain data, providing accurate air quality interpretations. The system classifies air quality into different ISPU categories (Good, Medium, Unhealthy, Very Unhealthy, Dangerous) in real-time. The study concludes that integrating IoT and fuzzy logic yields a high-performing, reliable air quality monitoring tool, significantly aiding pollution mitigation and public health. Further research is recommended to enhance algorithms and integrate additional technologies for improved functionality and accuracy.]]>
<![CDATA[Penerapan Oversampling Pada Klasifikasi Ujaran Kebencian Menggunakan Bidirectional Encoder Representations from Transformers ]]>
<![CDATA[Syahwaluddin, Risal]]>;
<![CDATA[Alita, Debby]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4295
<![CDATA[The problem of class imbalance is a common challenge in classification model building, especially in the context of hate speech. This study evaluates the effectiveness of the SMOTE oversampling technique in improving the performance of hate speech classification models using BERT. The dataset used has significant class imbalance, with the largest number of samples in the Hate class, followed by Offensive, and Neither. Two experiments were conducted: one without using SMOTE and one with SMOTE applied. Results showed that the application of SMOTE improved the overall model accuracy from 85% to 88%. Precision for the Offensive minority class increased from 0.33 to 0.45, although recall decreased from 0.45 to 0.28. In the Neither class, the F1-score increased, indicating an improvement in the balance between precision and recall. Performance on the majority Hate class remained stable, indicating that SMOTE did not interfere with the model's performance on the already dominant class. Overall, the application of SMOTE provides significant benefits in handling class imbalance, especially in improving precision for minority classes, resulting in a more accurate classification model.]]>
<![CDATA[Feature Model for Pet Health Application Domain using Feature Oriented Domain Analysis ]]>
<![CDATA[Satoh, Ajeng Nurhidayati A Darsan]]>;
<![CDATA[Budiardjo, Eko K.]]>;
<![CDATA[Mahatma, Kodrat]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4296
<![CDATA[According to a survey of Indonesian pet healthcare service users, only 19% of pet health applications are used since the functions offered by the applications are insufficient to meet the needs of the users. Developing feature model for the pet health application domain is the goal of this research. Using a mixed-methods approach, this research examined nine pet health apps which are available on Google Play and the App Store, observed 30 pet health service consumers through surveys using purposive sampling, and conducted document analyses. The Feature Oriented Domain Analysis (FODA) approach is applied within the Software Product Line Engineering (SPLE) framework. The result of this research is a pet health application domain feature model consisting of five non-functional requirements and 45 functional requirements. With an average assessment score of 96%, domain experts have determined that the feature model implementation in this study is in line with user needs.]]>
<![CDATA[ANALISIS PERBANDINGAN PERFORMA FHRP PADA ROUTING EIGRP MENGGUNAKAN IPV4 DAN IPV6 ]]>
<![CDATA[Wahyudi, Sandi]]>;
<![CDATA[Destya, Senie]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4297
<![CDATA[The limited capacity of IPv4, which only supports about 4.3 billion unique addresses, necessitated the development of a larger addressing system. IPv6 was developed to overcome this limitation, providing a wider range of addresses and improving address management and security. In a reliable and efficient network, mitigating failures and errors that can degrade Quality of Service (QoS) is important. QoS ensures that networks that require reliability, high bandwidth, or low latency can function optimally. One method to overcome network failures is to use First Hop Redundancy Protocol (FHRP), such as HSRP (Hot Standby Router Protocol) and GLBP (Gateway Load Balancing Protocol). This research shows that GLBP on IPv6 provides the best network performance compared to other protocols. GLBP on IPv6 achieves the highest throughput of 93,95130523 Bytes and the lowest delay of 1,000519298 seconds under normal conditions. In addition, under fault conditions, GLBP on IPv6 has the lowest downtime of 3.7 seconds and the lowest packet loss of 0.1%.]]>
<![CDATA[MUSIC SIMILARITY RANKING: STUDI KASUS FAIRPHONIC ]]>
<![CDATA[Kharisma, Rayhan]]>;
<![CDATA[Denny]]>
<![CDATA[ The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS) ]]>
Publisher : <![CDATA[AI Society & STMIK Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33022/ijcs.v13i4.4298
<![CDATA[Fairphonic Pte Ltd is a technology company operating in the music sector. Fairphonic provides services to detect content on social media that is suspected of copyright infringement. Fairphonic utilizes audio features for the detection process. The current algorithm used by Fairphonic requires pairwise comparison, and the content to be compared is collected through a scraping process immediately after the process is run. Fairphonic has hundreds of thousands of music data in their database. Fairphonic desires a more scalable algorithm to compare an input music piece with the entire Fairphonic music catalog. This research uses features such as Harmonic Pitch Class Profile (HPCP), Chroma, and Rhythm Pattern. The study compares previously researched algorithms, namely binary similarity matrix, Euclidean distance, and similarity matrix profile. The results show that the combination of HPCP with the binary similarity matrix yields the highest Mean Average Precision of 0.989. Speed testing by performing comparisons 10 times shows that the combination of Chroma and the similarity matrix profile is 72% faster compared to the combination of HPCP with the binary similarity matrix. The author recommends the Chroma and similarity matrix profile algorithm for music similarity ranking due to its faster process.]]>
