Claim Missing Document
Check
Articles

Found 32 Documents
Search

Prediction of Student Study Duration Using Multiple Linear Regression Method Fitri, Triyani Arita; Rahmawati; Lusiana; Rini Yanti
JAIA - Journal of Artificial Intelligence and Applications Vol. 3 No. 2 (2023): JAIA - Journal of Artificial Intelligence and Applications
Publisher : STMIK Amik Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33372/jaia.v3i2.1054

Abstract

Data mining is a process of extracting valuable and meaningful information from large or complex data sets. In the field of education, data mining can be used to predict the length of study of students by identifying factors that affect the length of study of students. This research aims to predict the length of study of students and to find out the most influential variables in completing the length of study. The method used in this research is the Multiple Linear Regression method. Training data as much as 292 data is taken from data on graduates from 2016 - 2018. While the testing data is taken from the active student data class of 2018 as much as 148 data. The model formed will be evaluated to determine the accuracy and RMSE values. The results showed that the Multiple Linear Regression method succeeded in carrying out the prediction process optimally with a percentage accuracy value of 85%, and an RMSE value of 0.76, which means that the error rate of this model is very low. Based on the resulting coefficient value, the SKS variable is the most influential variable in the length of study of students.
DESIGN THINKING APPROACH FOR OPTIMIZING TRANSACTION IN ANDROID-BASED CAMPUS CANTEENS Anam, M. Khairul; Kudadiri, Parlindungan; Hamdani, Hamdani; Fitri, Triyani Arita; Zoromi, Fransiskus
Jurnal Sistem Informasi dan Informatika (Simika) Vol 7 No 2 (2024): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v7i2.3357

Abstract

Android is extensively used by some startups for food ordering applications, such as go food, grab food, Shopee food applications. However, the application cannot be used in a small scope such as the canteen on campus. At STMIK Amik Riau, the existing canteens still use manual methods in ordering and payment, therefore to facilitate canteen transactions, innovation was carried out, namely by using the e-canteen application. This application was created to make it easier to order menus, find out what menus are on that day and to prevent purchases without making payments. The e-canteen application had several features such as the name of the canteen, selection of available menus, menu prices, and payment processing. The making of e-canteen used a design Thinking approach. Design Thinking is a creative approach that collects ideas directly from application users. Design thinking has several stages, such as: empathize, define, ideate, prototype and test. The testing process showed how the target users interacted with the prototype that had been created. The results obtained from this study demonstrated that the e-canteen application significantly facilitated canteen services by simplifying the ordering and payment processes. Specifically, users were able to place orders more efficiently and complete payments seamlessly, which improved overall user satisfaction and operational efficiency within the campus canteen.
Perbandingan Metode Learning Vector Quantization Dan Backpropagation Dalam Klasifikasi Personality Pada Anak Novita, Rita; Sujana, Teguh; Agusviyanda, Agusviyanda; Fitri, Triyani Arita; Susanti, Susanti
Computer Science and Information Technology Vol 5 No 3 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research focuses on classifying children's personalities at Rumah Bermain Bilal using Artificial Neural Network algorithms, specifically Learning Vector Quantization (LVQ) and Backpropagation. The primary objective of this study is to evaluate the effectiveness of these algorithms in categorizing children's personality data and to identify the most accurate method for educational settings. The experiments were conducted with various configurations, including the number of iterations and learning rate, to assess the performance of each algorithm comprehensively. The findings show that the LVQ method demonstrates higher accuracy than Backpropagation. For training data, LVQ achieved an accuracy of 73.47%, whereas Backpropagation reached only 40.82%. For test data, LVQ achieved an accuracy of 84.62%, significantly outperforming Backpropagation's 53.85%. These results indicate that LVQ is more effective in personality classification, especially in an educational context. It is hoped that these findings will assist educational institutions in implementing artificial intelligence-based methods to understand children's personality traits better, thereby supporting the development of more targeted teaching strategies.
Optimization of Deep Learning with FastText for Sentiment Analysis of the SIREKAP 2024 Application Handoko; Junadhi; Triyani Arita Fitri; Agustin
The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i2.4809

Abstract

This study analyzes public sentiment towards the SIREKAP 2024 application using deep learning. Data was collected from Google Playstore reviews and processed through cleaning, tokenization, and stemming. Word embedding was performed using FastText to capture more accurate word representations, including OOV words. The deep learning models compared were CNN, BiLSTM, and BiGRU. Performance evaluation used accuracy, precision, recall, and F1-score metrics. The results showed that the CNN model with FastText Gensim embedding achieved the highest accuracy of 95.98%, outperforming BiLSTM and BiGRU. This model was more effective in classifying positive and negative sentiments. This study provides insights for developers to improve the performance and public trust in SIREKAP 2024 and opens opportunities for further research with more complex embedding approaches and deep learning models.
PREDIKSI RISIKO KEBAKARAN MENGGUNAKAN ALGORITMA NAÏVE BAYES BERDASARKAN DATA HISTORIS DAN LINGKUNGAN Ismanizan, Ryan; Fitri, Triyani Arita; Rahmiati, Rahmiati; Agustin, Agustin
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.2352

Abstract

Fire is a disaster that can cause significant material and human losses. Kampar Regency in Indonesia is a fire-prone area due to short circuits, human negligence, and environmental conditions. This study aims to predict fire risk based on historical fire incident data and environmental factors using the Naïve Bayes algorithm. This method was chosen because of its ability to classify large-dimensional data with high probability. The research stages include data collection, preprocessing, data exploration, modeling, and model evaluation. Data were tested using splits of 70:30, 80:20, and 90:10. The results showed that the Naïve Bayes algorithm was able to provide prediction accuracy levels of 95.82%, 96.00%, and 95.45%, respectively. The highest accuracy level was obtained in the 80:20 scenario. These findings indicate that Naïve Bayes is effective in predicting high-risk areas for fire and can serve as a reference for relevant parties in developing more targeted fire prevention and mitigation policies.
Prediction of Library Book Borrowing Patterns Using The Random Forest Algorithm Ega Ranaldi Pebriansyah; Susanti; Rahmiati; Triyani Arita Fitri
Jurnal Riset Informatika Vol. 7 No. 4 (2025): September 2025
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (870.043 KB) | DOI: 10.34288/jri.v7i4.409

Abstract

Libraries play a crucial role in supporting the improvement of public literacy by providing reading materials tailored to users' needs and interests. One of the challenges faced by the Bukit Batu District Public Library is that the collection acquisition analysis process is not yet based on comprehensive borrowing patterns, potentially resulting in inaccurate results. This study aims to predict book borrowing patterns and classify collections into popular and unpopular categories using the Random Forest algorithm. Historical book borrowing data from 2019 to 2024 was used as the primary source in the model training and testing process. Testing was conducted with three data sharing ratios, namely 70:30, 80:20, and 90:10, which resulted in prediction accuracy of 89.19%, 88.69%, and 86.74%, respectively. Based on the analysis results, mathematics books were identified as the most popular collection with 146 borrowings, while social studies books were categorized as unpopular with 122 borrowings. These findings are expected to serve as a reference for libraries in formulating more effective, efficient, and data-based collection management strategies, thereby increasing the relevance and attractiveness of collections for users and supporting the optimization of library services.
Analisis Pilkada Medan pada Sosial Media Menggunakan Analisis Sentimen dan Social Network Analyisis Anam, M. Khairul; Firdaus, Muhammad Bambang; Fitri, Triyani Arita; Lusiana; Agustin, Wirta; Agustin
The Indonesian Journal of Computer Science Vol. 11 No. 1 (2022): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v11i1.3027

Abstract

The simultaneous regional head elections were over, but during the campaign until it was decided to become regional head there were many comments, both pro and contra. The city of Medan is one of the regions that will hold the 2020 ELECTION during the pandemic. The Medan City Election has decided that the pair Bobby Nasution and Aulia Rachman have won. This victory certainly gets a variety of comments on social media, especially Twitter. This study conducts sentiment analysis to see the sentiment that occurs, namely seeing negative, positive, or neutral comments. This sentiment analysis uses two methods to see the resulting accuracy, namely Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC). This study also looks at the interactions that occur using Social Network Analysis (SNA). In addition to sentiment analysis and SNA, this study also looks at the existence of BOT accounts used in the #PilkadaMedan. The results obtained from the sentiment analysis show that NBC has the highest accuracy, which is 81, 72% with a data proportion of 90:10. Then on SNA, the @YanHarahap account got the highest nodes, namely 911 nodes. Then from 10326 tweets, 11% were suspected of being BOT by the DroneEmprit Academic system.
Perbandingan Algoritma XGBoost dan SVM Dalam Analisis Opini Publik Pemilihan Presiden 2024 Safitri, Dea; Susanti; Rahmaddeni; Fitri, Triyani Arita
The Indonesian Journal of Computer Science Vol. 13 No. 3 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i3.4041

Abstract

Pemilihan presiden dipengaruhi oleh berbagai faktor, termasuk latar belakang kandidat, masalah politik, dan preferensi ideologis, menjadikan pemilihan presiden sebagai subjek klasifikasi yang kompleks dan menarik. Menganalisis sentimen publik terhadap kandidat dan isu-isu politik memberikan wawasan penting tentang dinamika politik selama pemilihan. Penelitian ini berfokus pada pemilihan presiden dan membandingkan kinerja dua algoritma klasifikasi populer, XGBoost dan SVM, untuk menentukan metode mana yang lebih efektif. Setelah beberapa preprocessing teks dari 562 tweet, kami menemukan bahwa mayoritas pengguna Twitter cenderung memilih 347 tweet "Prabowo". Model Extreme Gradient Boosting (XGBoost) menunjukkan performa terbaik dengan presisi 78%, presisi 76%, recall 78%, dan skor f1 76%. Hasil ini menunjukkan bahwa XGBoost adalah model terbaik untuk mengklasifikasikan opini publik terkait pemilihan presiden 2024 dan memberikan kontribusi penting untuk memahami efektivitas metode klasifikasi dalam konteks pemilihan presiden.
OPTIMASI TEKNIK VOTING PADA SENTIMEN ANALISIS PEMILIHAN PRESIDEN 2024 MENGGUNAKAN MACHINE LEARNING Kharisma Rahayu; M. Khairul Anam; Lusiana Efrizoni; Nurjayadi; Triyani Arita Fitri
The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i4.4119

Abstract

The presidential election is an important event in the democratic system of the Unitary State of the Republic of Indonesia or NKRI held every five years. There are many pros and cons of the presidential election, especially on social media Twitter or X. X is one of the media platforms where people leave positive, neutral, and even negative comments. Therefore, this research aims to build a sentiment analysis model to classify the sentiment of the 2024 presidential election. This research uses the Support Vector machine, Naïve Bayes and Decision Tree algorithms in performing classification with the addition of the Syntethic Minority Over-Sampling and Ensemble Voting methods. The test results show that public sentiment towards the presidential election dominates negative sentiment of 5008 positive 3582 and neutral 1411 sentiments. Then the results of data processing SVM, NB and DT algorithms plus SMOTE and ensemble voting optimization, provide 92.8% accuracy, 93% precision, 93% recall and 93% F1-Score. This research can make a significant contribution by classifying public sentiment towards the 2024 presidential election data.
ANALISIS KESIAPAN SEKOLAH MENENGAH DALAM MENERAPKAN E-VOTING MENGGUNAKAN MODEL TECHNOLOGY READINESS INDEX Hazira, Nadila; Anam, M. Khairul; Agustin, Wirta; Fitri, Triyani Arita; Zamsuri, Ahmad; Syam, Salmaini Safitri
ZONAsi: Jurnal Sistem Informasi Vol. 6 No. 2 (2024): Publikasi Artikel ZONAsi: Periode Mei 2024
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/zn.v6i2.18400

Abstract

Voting can be interpreted as a way of making decisions based on the largest number of votes. So far, voting is carried out by ticking or voting on a ballot paper as an option in holding the election for OSIS chairman at SMAN 15 Pekanbaru. This method is considered still very conventional amidst advances in technology and information which has weaknesses in terms of efficiency and effectiveness. The weaknesses of conventional voting are: the decision is not the result of consensus, some participants are forced to accept the decision that has been taken, some participants often do not accept the decision, the aspirations of the participants are not fully channeled. To reduce problems arising from manual voting, it is necessary to analyze the readiness of secondary schools in implementing e-voting using the Technology Readiness Index model. The method that can be used to measure the level of user readiness in using technology is the Technology Readiness Index (TRI). In order to find out the results of the analysis and test the readiness of secondary schools in implementing the new system, the author will conduct a survey by distributing a Google Form link containing a list of statements regarding the readiness of secondary school residents, especially at SMAN 15 Pekanbaru, in using the web-based E-Voting system for the election of chairman. Student Council. The survey results will be analyzed using the SPSS 25.0 application and also calculated using the Technology Readiness Index Method