Claim Missing Document
Check
Articles

Automatic prediction of learning styles: a comprehensive analysis of classification models Lestari, Uning; Salam, Sazilah; Choo, Yun-Huoy; Alomoush, Ashraf; Al Qallab, Kholoud
Bulletin of Electrical Engineering and Informatics Vol 13, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i5.7456

Abstract

Learning styles are a topic of interest in educational research about how individuals acquire and process information in offline or online learning. Identification of learning styles in the online learning environment is challenging. The existing approaches for the identification of learning styles are limited. This study aims to review the many learning styles characterized by various classification approaches toward the automatic prediction of learning styles from learning management system (LMS) datasets. A systematic literature review (SLR) was conducted to select and analyze the most pertinent and significant papers for automatically predicting learning styles. Fifty-two research papers were published between 2015-2023. This research divides analysis into five categories: the classification of learning style models, the collection of the collected dataset, learning styles based on the curriculum, research objectives related to learning styles, and the comprehensive analysis of learning styles. This study found that learning style research encompasses diverse theories, models, and algorithms to understand individual learning preferences. Statistical analysis, explicit data collection, and the Felder-Silverman model are prevalent in research, highlighting the significance of algorithm improvement for optimizing learning processes, particularly in computer science. The categorization and understanding of various methods offer valuable insights for enhancing learning experiences in the future.
Empirical analysis of language learning strategies for optimizing online language courses Lip, Rashidah; Salam, Sazilah; Mohamad, Siti Nurul Mahfuzah; Kar Mee, Cheong; Poh Ee, Tan; Ismail, Nurmaisarah; Mohd Yusoff, Azizul; Lestari, Uning; Ahmad Fesol, Siti Feirusz
International Journal of Evaluation and Research in Education (IJERE) Vol 13, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijere.v13i6.29418

Abstract

In today’s changing education world, online language classes are becoming more important. Recognizing the important role of the relationship between language learning strategies and students’ preferences, our empirical study examines the patterns or factors that explain the observed correlations among variables to provide insights in optimizing online language courses. Addressing a critical gap in the existing literature that has traditionally treated language learning strategies and online language education as distinct entities, our survey-based research collected comprehensive data from students enrolled in online language courses. Focused on six key language learning strategies: memory, cognitive, compensation, metacognitive, affective, and social. The research shows a delicate connection between these strategies and students’ preferences in online teaching mode. The empirical findings provide insights into certain strategies that work better for specific online learning methods. This helps us grasp the varied preferences of groups of students. This research enriches online language education by revealing an unexplored connection between strategies and preferences and provides a valuable resource for educators and course designers. The information given helps make online language classes better. It ensures that students learn languages more effectively online, considering their functional and practical needs in online learning.
Comparison of Feature Selection with Information Gain Method in Decision Tree, Regression Logistic and Random Forest Algorithms Sholeh, Muhammad; Lestari, Uning; Andayati, Dina
Journal of Applied Business and Technology Vol. 5 No. 3 (2024): Journal of Applied Business and Technology
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/jabt.v5i3.155

Abstract

One of the approaches that can be done is to perform feature selection. Feature selection is done by identifying the most informative features and not using features that do not directly contribute to the target feature. The purpose of feature selection is to increase the accuracy of the model. The research was conducted by comparing the performance of the model by comparing the accuracy results of the model without any feature selection with the model that has done feature selection. The process is done by comparing the accuracy results with decision tree, random forest and SVM algorithms. In the research method of feature selection on science data, the steps include understanding the domain and dataset, exploratory analysis, data cleaning, measuring feature relevance with criteria such as Information Gain, and feature ranking. The results are evaluated and validated using model performance metrics before and after feature selection. This process ensures selection of relevant features, improving accuracy. The research process used the Lung Cancer Prediction datasheet which consists of 306 rows and 16 attributes. The results show that feature selection can improve the performance of the classification model by reducing features that do not contribute to the target. Comparison results using decision tree, Regression Logistic and random forest classification model algorithms and feature selection resulted in a high accuracy value of 0.968 in the Regression Logistic algorithm with a feature selection of 5.
SISTEM PENDUKUNG KEPUTUSAN KLASIFIKASI KELUARGA MISKIN MENGGUNAKAN METODE SIMPLE ADDITIVE WEIGHTING (SAW) SEBAGAI ACUAN PENERIMA BANTUAN DANA PEMERINTAH (STUDI KASUS: PEMERINTAH DESA TAMANMARTANI, SLEMAN) Uning Lestari; Muhammad Targiono
Jurnal TAM (Technology Acceptance Model) Vol 8, No 1 (2017): Jurnal TAM (Technology Acceptance Model)
Publisher : LPPM STMIK Pringsewu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/jurnaltam.v8i1.97

Abstract

Various types of government programs in poverty alleviation efforts have been widely implemented, but the assistance that reached the hands of the people has not been in accordance with what is expected. One reason is that the determination of the status of poor families as beneficiaries has not been optimal, so that in providing poverty assistance has not been well targeted. Application Development Decision Support System Determination of Poor Family is made by the method used in determining the decision is the method of Simple Additive Weighting (SAW). The results of the assessment conducted by the system are given poverty status such as Very Poor, Poor, Vulnerable Poor and Not Poor. SAW method is chosen because it can determine the weight value for each attribute, then proceed with the ranking process that will select the best alternative from a number of alternatives, in this case the alternatives referred to are families categorized as poor families based on the criteria specified. With the ranking process, the assessment will be more precise because it is based on predetermined criteria and weights, so it will get more accurate results for anyone who is categorized as poor. These results can then form the basis for the TPK (Poverty Reduction Team) team of Tamanmartani villages to determine which families are entitled to receive government funding so that the distribution of aid is targeted.
APPLICATION OF HOME LIGHT CONTROL SYSTEM USING ARDUINO WITH MOBILE BASED WIFI MEDIA Uning Lestari; Erfanti Fatkhiyah; Andung Febi Prakoso
IJISCS (International Journal of Information System and Computer Science) Vol 2, No 2 (2018): IJISCS (International Journal of Information System and Computer Science)
Publisher : Bakti Nusantara Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/ijiscs.v2i2.606

Abstract

Nowadays, technology development encourage people to think creatively, not not only to explore new discoveries, but also to maximize existing technological performance to ease human work in everyday life. The need for an automatic control system is needed with the increasing activity of each individual community with various erratic activities and times. As a result, many activities in the household are delayed, such as turning on or turning off the lights in every room at night and in the morning. Smart home system is one solution that suits the needs of the current automatic controllers. Smart home system is a home or building is equipped with an integrated technology with the help of the tool/tools which can be a computer or other device, for example a smartphone to provide all the comfort, safety, security and energy saving is automatic and programmed. The smart home system can be used to control almost all equipment and equipment at home, from lighting settings to various household appliances, which can be done only by using sound, infrared light or remote control. In this study, a smart home system was created for home light control system applications using Arduino Uno microcontroller via mobile-based wifi media. With this application the user can control the home lights by turning off or turning on the home lights remotely through the mobile media. Thus the efficiency of electricity use becomes more maintained.
Augmented Reality Technology for the Introduction of Mobile-Based Spaces with the Hough Transform Method (Case Study: Akprind Institute of Science and Technology Campus Locations) Galuh Ayu Novilia; Uning Lestari
JTKSI (Jurnal Teknologi Komputer dan Sistem Informasi) Vol 4, No 1 (2021): JTKSI
Publisher : Institut Bakti Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/jtksi.v4i1.978

Abstract

AKPRIND Institute of Science Technology (IST AKPRIND) Yogyakarta is one of the private universities in Yogyakarta which has 3 different building locations so that it has many rooms and buildings in a large area. In addition, the shape of the room is similar and the lack of information and the location of the campus which is divided into three, often makes it difficult for new students to find a room to carry out the lecture process later. Augmented Reality (AR) is a concept of combining virtual reality with world reality (real life), so that 2-dimensional (2D) or 3-dimensional (3D) virtual objects seem to look real and blend into the real world. The AR camera will capture and identify markers and then position and place a virtual data object on the marker. In the process of creating an AR application, Unity3D tools and a database using Vuforia are required. The results of the application will be tested using the Standard Hough Transform (SHT) method. SHT is tested to get a conclusion about the detection distance value at the distance between the image and the camera. The test was carried out using 3 marker sizes with a tilt angle of 0 °, 15 °, 30 °, 45 °, 60 °, 75 °, and 90 ° carried out with 20 watts of lamp lighting and a distance of 2.5 meters between the lamp and the marker. Based on testing with the SHT method, the larger the marker size, the farther the marker distance can be detected.
Effect of Hyperparameter Tuning on Performance on Classification model Sholeh, Muhammad; Lestari, Uning; Andayati, Dina
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 1, June 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i1.11735

Abstract

This research aims to analyze the effect of hyperparameter tuning on the performance of Logistic Regression, K-Nearest Neighbours, Support Vector Machine, Decision Tree, Random Forest, Random Forest Classifier, Naive Bayes algorithms.  These six algorithms were tested both using hyperparameter tuning and not using hyperparameter tuning. The dataset used in this research is a public dataset, namely the heart datasheet. This datasheet contains information about features related to the diagnosis of heart disease. Hyperparameter tuning is performed using a grid search technique to determine the best combination of hyperparameter values that can improve model accuracy. Performance comparison is done by measuring the accuracy, precision, recall, and F1-score of each algorithm before and after tuning. The research method follows the stages in the Knowledge Discovery in Databases (KDD) methodology. The KDD methodology consists of several stages of data collection, data cleaning to remove errors, data integration from various sources, and data selection and transformation to be ready for analysis. Next, data mining is performed to find patterns or relationships in the data and evaluation and interpretation of the results to ensure their validity. The results show that hyperparameter tuning applied to the six algorithms does not necessarily improve performance. In the algorithm. SVM and decision tree algorithms, the performance results before hyperparameter tuning actually have a higher accuracy value. The performance of algorithms that experienced an increase after hyperparameter tuning was logistic regression and K-Nearest neighbours. The same performance results are generated in the Random Forest and Naive Bayes algorithms. Based on testing the six algorithms and using the heart datasheet, the hyperparameter tuning process does not always result in a better performance value.
ANALISIS PREDIKSI TUMBUH KEMBANG ANAK DENGAN MACHINE LEARNING Nugraheni, Murien; Widodo, Widodo; Lestari, Uning; Effendy, Vina Ardelia; Yunanto, Prasetyo Wibowo; Amannu, Ramadhan
Infotech: Journal of Technology Information Vol 11, No 1 (2025): JUNI
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i1.389

Abstract

Stunting is a major chronic nutritional issue that remains a significant challenge in Indonesia. This study aims to predict the risk of stunting in children and enhance prevention efforts by analyzing the health and nutritional status of parents. The research employs Machine Learning methods by comparing the performance of the Decision Tree and Gaussian Naive Bayes algorithms. The dataset was obtained from open data sources and analyzed using Google Colab, with a Technology Readiness Level (TRL) of level 3. Evaluation results show that both algorithms achieved an accuracy of 95.35% based on the confusion matrix. The model accurately identified 2 stunting cases (True Positive) and 41 non-stunting cases (True Negative), indicating a high level of classification reliability. These findings suggest that Machine Learning approaches can be effectively utilized as early detection tools to support stunting prevention strategies in children.
Prediction And Detection Of Type II Diabetes Mellitus Using The K-Nearest Neighbor Algorithm Lestari, Uning; hamzah, amir; Paays, Franco Albertino Karel
Telematika Vol 21 No 2 (2024): Edisi Juni 2024
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v21i2.12384

Abstract

Purpose: High blood sugar causes Mellitus (DM), a metabolic disorder. DM affects human metabolism and causes many complications, such as heart disease, kidney problems, skin disorders, and slow healing. Therefore, using machine learning algorithms to implement an automatic diabetes diagnosis system is crucial for predicting DM.Design/methodology/approach: This research created a DM disease prediction system using machine learning with the K-Nearest Neighbor algorithm. The National Institute of Diabetes and Digestive and Kidney Diseases, Hospital Frankfurt, Germany, and the results of health surveys and medical research are the sources of two separate datasets used in the Kaggle platform data. The stages in Machine Learning include data merging, data cleaning, and data splittingFindings/result: This research produces the best prediction model at a ratio of 70:30, with the lowest MSE value on testing data, 0.217. With K Folding Cross-validation, it makes an average accuracy of 73.88%.Originality/value/state of the art: This research creates a prediction model for diabetes mellitus type 2 using two different datasets with 9 features. It makes a Machine Learning model using the KNN algorithm by importing the KneighborClassifier and evaluating it using the MSE (Mean Square Error) matrix and K Folding cross-validation to determine modelling accuracy
Hyperparameter Optimization Using Grid Search and Random Search to Improve the Performance of Prediction Models with Decision Trees Sholeh, Muhammad; Lestari, Uning; Andayati, Dina
Jurnal Riset Multidisiplin dan Inovasi Teknologi Том 3 № 03 (2025): Jurnal Riset Multidisiplin dan Inovasi Teknologi
Publisher : PT. Riset Press International

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59653/jimat.v3i03.2025

Abstract

Hyperparameter selection to obtain optimal accuracy results is an important factor in improving model performance in data science. This study discusses a comparison of two hyperparameter optimization methods, namely Grid Search and Random Search, in the Decision Tree Classifier algorithm using the Breast Cancer Wisconsin (Diagnostic) Dataset from the UCI Machine Learning Repository. The dataset contains 569 samples with 30 numerical features describing the characteristics of breast cancer cells, such as mean radius, texture, perimeter, area, and smoothness, which are classified into two classes, namely malignant and benign. This study uses the CRISP-DM approach, which includes the stages of business understanding, data understanding, data preparation, modeling, and evaluation. In the modeling stage, three testing scenarios were conducted, namely the Decision Tree model without tuning, the model with Grid Search optimization, and the model with Random Search optimization. Performance evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The results showed that hyperparameter optimization had a significant effect on model performance. The Decision Tree model without tuning produced an accuracy of 92.98%, while the model with Grid Search achieved the highest accuracy of 95.61%, and Random Search obtained an accuracy of 97.37%. Thus, it can be concluded that Grid Search provides the most optimal results in finding the best parameter combination, even though it requires longer computation time compared to Random Search.
Co-Authors -, Marwoto -, Marwoto Abdulloh, Yusuf Agusalim Syamsudin Pure Ahmad Fesol, Siti Feirusz Ahmad Zarkasi Akhir, Muhammad Al Qallab, Kholoud Alomoush, Ashraf Amannu, Ramadhan Amir Hamzah Amir Hamzah Andri Harsono Andri Harsono, Andri Andung Febi Prakoso Anggraeni, Ari Puspratini Annafi’ Franz Aprilianti, Yunis Aprilianti Ardiansyah - Arga, Dwi Asih Sapta Arifuddin, Arham Ariyana, Renna Yanwastika Asti Widyaningsih Aziz Nurwahidin Bondan Prawiro Yudo, Bondan Prawiro Cardoso, Noel Adriano Catur Iswahyudi Choo, Yun-Huoy Dani Heriyanto Dani Yulkarnain Debby Anugrahni Deby Saputra, Deby Dede Hernowo Deserius Marianus Oenunu Dina Andayati Dina Andayati Dini Pujiatin Edhy Sutanta (Jurusan Teknik Informatika IST AKPRIND Yogyakarta) Effendy, Vina Ardelia Eko Budianto Erfanti Fatkhiyah Erfanty Fatkhiyah Erma Susanti Erna Kumalasari Erna Kumalasari Nurnawati Erna Kumalasari Nurnawati Erni Astuti Firmansyah Surwa Adi L Galuh Ayu Novilia Hari Wibowo Hendrati, Rr. Dina Oktavia Indra Kurniawan Ismail, Nurmaisarah iswanto Iswayudi, Catur Jepri Ardianto Joko Triyono Juliyanti, Nur Arifah Kar Mee, Cheong Laksono Trisnantoro Lip, Rashidah Listyaningrum, Desti Arghina Luay Nabila El Suffa M. Abdul Alim Alami Mohamad, Siti Nurul Mahfuzah Mohd Yusoff, Azizul Muchamad Rizal Rinaldi MUHAMMAD SHOLEH Muhammad Targiono Muntaha Nega Murien Nugraheni Naniek Widyastuti Naniek Widyastuti Nurmansyah Oktavina Marlina Roma Paays, Franco Albertino Karel Parasian D.P Silitonga Poh Ee, Tan Prastika, Dika Priska Prihsmoro1, Catur Dwi Prita Haryani Pujiatin, Dini Rendi Saputra Rr Yuliana Rachmawati K RR. Yuliana Rachmawati Salam, Sazilah Saldanha, Paulino Sholeh, Muhammad Siti Saudah Sony Cahyo Wibisono Sony Cahyo Wibisono, Sony Cahyo Sugiyatno Sugiyatno Supriyanri, Sri Suraya Suraya Suwanto Raharjo Triyono, Joko Utami Hayati Victor Motumona Wafikulinuha Wafikulinuha Waliadi, Julfikar Wandy Damarullah Widodo Widodo Wiwik Handayani Yeremias Budi Liman Hege Yeremias Budi Liman Hege, Yeremias Budi Liman Yunanto, Prasetyo Wibowo Yunis Aprilianti Yusron - Zulfikar .L, Fauzul Rachman