cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Firdaus Annas
Contact Email
info@makwadfoundation.org
Phone
+6285278566869
Journal Mail Official
intellect.makwafoundation@gmail.com
Editorial Address
Jl. Dusun Pandam Jorong Aro Kandikir Nagari Gadut Kecamatan Tilatang Kamang Kabupaten Agam Sumatera Barat
Location
Kab. agam,
Sumatera barat
INDONESIA
Intellect : Indonesian Journal of Learning and Technological Innovation
Published by Yayasan Lembaga Studi Makwa
ISSN : -     EISSN : 29629233     DOI : -
Core Subject : Science, Education, Engineering,
Computer Science & IT Education Electrical & Electronics Engineering
The Intellect : Indonesian Journal of Learning and Technological Innovation aims to promote research and scholarship on the innovation of technology in secondary and higher education, as well as promote effective practice, and inform policy in education. The Intellect publishes papers related to theoretical foundations, design, analysis and implementation, as well as effectiveness and impact issues related to learning technology. The Intellect : Indonesian Journal of Learning and Technological Innovation published by Yayasan Lembaga Studi Makwa (Makwa Foundation)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 110 Documents
 7   8   9   10   11 
Klasifikasi Aksesori Fashion Berdasarkan Fitur Citra Menggunakan K-Means Clustering Zebbil Billian Tomi; Agung Ramadhanu
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1476

Abstract

The rapid development of computer vision and machine learning has enabled new applications in the fashion industry, particularly in image-based product classification and recommendation systems. This study aims to classify fashion accessories, namely wallets, bags, and belts, based on image features using the K-Means clustering algorithm. The dataset consists of 30 images acquired under controlled conditions with uniform lighting, resolution, and background. Although the dataset size is relatively limited, this study is designed as an initial baseline to evaluate the effectiveness of K-Means clustering on small and homogeneous datasets, which are commonly encountered in early-stage image classification research. The research workflow includes image preprocessing (resizing, color space conversion, and noise reduction), object segmentation, and feature extraction focusing on color, texture, and shape characteristics. The extracted features include Local Binary Pattern (LBP), entropy, edge density, eccentricity, extent, and area ratio. The results demonstrate that K-Means clustering is capable of grouping fashion accessories into distinct categories according to their visual characteristics. From a practical perspective, the proposed approach can be applied to automated fashion product cataloging to support inventory management, image-based product search, and recommendation systems in e-commerce platforms. This study provides a simple and interpretable baseline for fashion accessory classification and serves as a foundation for future work involving larger datasets, advanced feature descriptors, or deep learning-based methods. Abstrak Perkembangan computer vision dan machine learning memungkinkan penerapan baru dalam industri fesyen, khususnya pada sistem klasifikasi dan rekomendasi produk berbasis citra. Penelitian ini bertujuan mengklasifikasikan aksesori fesyen berupa dompet, tas, dan ikat pinggang berdasarkan fitur citra menggunakan algoritme K-Means clustering. Dataset yang digunakan terdiri dari 30 citra yang dikumpulkan dalam kondisi terkontrol dengan pencahayaan, resolusi, dan latar belakang seragam. Meskipun jumlah dataset relatif terbatas, pendekatan ini dirancang sebagai studi awal (baseline) untuk mengevaluasi efektivitas K-Means pada dataset kecil dan homogen yang umum dijumpai pada tahap awal pengembangan sistem klasifikasi berbasis citra. Tahapan penelitian meliputi preprocessing (penyeragaman ukuran, konversi warna, dan reduksi noise), segmentasi objek, serta ekstraksi fitur warna, tekstur, dan bentuk. Fitur yang digunakan meliputi Local Binary Pattern (LBP), entropi, kerapatan tepi, eksentrisitas, extent, dan rasio area. Hasil penelitian menunjukkan bahwa algoritme K-Means mampu mengelompokkan aksesori fesyen ke dalam kategori yang berbeda berdasarkan karakteristik visualnya. Secara praktis, hasil penelitian ini berpotensi diterapkan sebagai sistem klasifikasi otomatis pada katalog produk fesyen digital untuk mendukung manajemen inventori, pencarian produk berbasis citra, serta sistem rekomendasi pada platform e-commerce. Penelitian ini diharapkan dapat menjadi baseline sederhana dan interpretatif dalam klasifikasi aksesori fesyen, serta menjadi pijakan untuk pengembangan lanjutan menggunakan dataset yang lebih besar, deskriptor fitur modern, maupun metode berbasis deep learning.
Transformasi Digital Layanan Akademik Melalui Sistem Informasi Pengajuan Tugas Akhir Online Berbasis Design Science Research Muhammad Rinov Cuhanazriansyah; Marlina Yuliyanti; Ahmad Aniko Misbakhul Umam; Ayu Miftakhatul Awaliyah
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1487

Abstract

The need for increased efficiency, transparency, and quality of academic services is one of the main implications of digital transformation in higher education. This study aims to develop and implement an Online Final Project Submission Information System (SIM Skripsi) as part of efforts to transform digital academic services at IKIP PGRI Bojonegoro. The approach used is Design Science Research (DSR), which includes the stages of problem identification, system design and implementation, and artefact evaluation. The system was developed using Laravel and MySQL with a modular architecture based on microservices and Docker, then tested through trials involving students, supervisors, and academic administration staff. The results of the study show that the implementation of SIM Skripsi significantly accelerated the final project submission process, with an average duration reduction from 7–8 working days to 1–2 working days. The level of user satisfaction, measured using the System Usability Scale (SUS), obtained an average score of 82.4, which is classified as very good, while the system reliability level reached 97.8 per cent. These findings indicate that the Thesis Management System is capable of supporting academic administration efficiency, increasing user acceptance, and strengthening the transparency of the service process. Considering the readiness of technological infrastructure, institutional policy support, and human resource capacity, this system has the potential to be adapted and implemented in other higher education institutions with comparable characteristics. Abstrak Kebutuhan untuk meningkatkan efisiensi, transparansi, dan kualitas layanan akademik merupakan hasil dari transformasi digital di lingkungan pendidikan tinggi. Tujuan penelitian ini adalah untuk mengembangkan dan mengimplementasikan Sistem Informasi Pengajuan Tugas Akhir Online (SIM Skripsi) sebagai bagian dari transformasi akademik digital di IKIP PGRI Bojonegoro. Metodologi yang digunakan adalah Design Science Research (DSR), yang meliputi identifikasi masalah, implementasi sistem menggunakan Laravel dan MySQL, arsitektur sistem berbasis microservices dan Docker, serta evaluasi melalui uji coba kepada mahasiswa, dosen, dan staf administrasi. Temuan penelitian menunjukkan bahwa durasi proses pembelajaran tugas akhir berkurang secara signifikan dari rata-rata 7-8 hari menjadi 1-2 hari. Berdasarkan Skala Usability Sistem (SUS), kepuasan pengguna mencapai skor rata-rata 82,4, yang masuk dalam kategori “sangat baik”, sementara keandalan sistem mencapai 97,8%. Hal ini menunjukkan bahwa implementasi SIM Skripsi dapat meningkatkan proses, meningkatkan kepuasan pengguna, dan meningkatkan transparansi layanan akademik. Melalui optimasi jaringan dan peningkatan fitur tambahan, sistem ini berpotensi untuk diterapkan secara luas oleh perguruan tinggi lainnya.
Evaluasi Interaktif dalam Pembelajaran Informatika: Studi Penggunaan Zep Quiz untuk Evaluasi Berbasis Game Rahma Dina Fitri; Supriadi Supriadi; Darul Ilmi; Supratman Zakir
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1509

Abstract

The aim of this research is to design educational game-based learning evaluation media using the Zep Quiz platform which is expected to be a solution for evaluating Informatics learning that is more interactive, effective and efficient compared to conventional evaluation using physical answer sheets, as well as increasing student involvement in the evaluation process. This research is based on the results of interviews with class VII Informatics subject teachers at SMPN 6 Bukittinggi as well as direct observations in class, which show that the learning evaluation process still uses conventional media in the form of physical answer sheets. This condition makes students feel bored and less motivated, while teachers face obstacles in checking and recording evaluation results because they are still done manually. To overcome these problems, this research applies the Research and Development (R&D) method with the ADDIE model which includes analysis, design, development, implementation and evaluation stages. Validity testing was carried out using Aiken's V, practicality testing using Cohen's Kappa, and effectiveness testing using Hake's G-Score. The research results showed that the Zep Quiz-based evaluation media was declared valid with an average score of 0.86, practical with an average score of 0.93, and effective with an average score of 0.83. The contribution of this research is to present educational game-based learning evaluation media using Zep Quiz which is valid, practical and effective, so that it can be an alternative solution for teachers in carrying out learning evaluations that are more interactive, efficient and able to increase student motivation. Abstrak Tujuan dari penelitian ini adalah merancang media evaluasi pembelajaran berbasis game edukasi menggunakan platform Zep Quiz yang diharapkan dapat menjadi solusi evaluasi pembelajaran Informatika yang lebih interaktif, efektif, dan efisien dibandingkan evaluasi konvensional menggunakan lembar jawaban fisik, serta meningkatkan keterlibatan siswa dalam proses evaluasi. Penelitian ini didasari oleh hasil wawancara dengan guru mata pelajaran Informatika kelas VII SMPN 6 Bukittinggi serta observasi langsung di kelas, yang menunjukkan bahwa proses evaluasi pembelajaran masih menggunakan media konvensional berupa lembar jawaban fisik. Kondisi tersebut membuat siswa merasa jenuh dan kurang termotivasi, sementara guru menghadapi kendala dalam pemeriksaan dan perekapan hasil evaluasi karena masih dilakukan secara manual. Untuk mengatasi permasalahan tersebut, penelitian ini menerapkan metode Research and Development (R&D) dengan model ADDIE yang mencakup tahap analisis, desain, pengembangan, implementasi, dan evaluasi. Uji validitas dilakukan dengan menggunakan Aiken’s V, uji praktikalitas dengan Cohen’s Kappa, dan uji efektivitas dengan G-Score Hake. Hasil penelitian menunjukkan bahwa media evaluasi berbasis Zep Quiz dinyatakan valid dengan skor rata-rata 0,86, praktis dengan skor rata-rata 0,93, dan efektif dengan skor rata-rata 0,83. Kontribusi penelitian ini adalah menghadirkan media evaluasi pembelajaran berbasis game edukasi menggunakan Zep Quiz yang valid, praktis, dan efektif, sehingga dapat menjadi solusi alternatif bagi guru dalam melaksanakan evaluasi pembelajaran yang lebih interaktif, efisien, dan mampu meningkatkan motivasi siswa.
Model Sistem Pendukung Keputusan untuk Penentuan Dosen Pembimbing Skripsi dengan Metode Profile Matching Adri Maulana Zahari; Liza Efriyanti; Supratman Zakir; Riri Okra
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1513

Abstract

Thesis supervisors play an important role in maintaining academic quality and supporting students’ timely completion of their studies. However, at the Faculty of Tarbiyah and Teacher Training, UIN Sjech M. Djamil Djambek Bukittinggi, the assignment of thesis supervisors is still conducted manually, potentially causing procedural inefficiency, unequal supervision workloads, and limited access for students. This study aimed to develop a decision support system for thesis supervisor assignment using the Profile Matching method to align lecturers’ competencies with students’ thesis topics. The study employed a Research and Development (R&D) approach using the Waterfall model, which included needs analysis, system design, implementation, and testing. The result of this study is a decision support system that assists the Head of Study Program in assigning supervisors more objectively, evenly, and efficiently, while also facilitating electronic thesis title submission. The system was developed with reference to the ISO 25010 software quality standard to ensure its functionality and reliability. This study contributes to the development of decision support systems in higher education academic services through the application of Profile Matching for a more objective and structured thesis supervisor assignment process. Abstrak Dosen Pembimbing Skripsi (DPS) berperan penting dalam menjaga mutu akademik dan mendukung penyelesaian studi mahasiswa secara tepat waktu. Namun, di Fakultas Tarbiyah dan Ilmu Keguruan (FTIK) UIN Sjech M. Djamil Djambek Bukittinggi, penentuan DPS masih dilakukan secara manual, sehingga berpotensi menimbulkan inefisiensi, ketidakmerataan beban bimbingan, dan hambatan akses bagi mahasiswa. Penelitian ini bertujuan mengembangkan sistem pendukung keputusan penentuan DPS menggunakan metode Profile Matching agar rekomendasi dosen pembimbing sesuai dengan kompetensi dosen dan topik skripsi mahasiswa. Penelitian ini menggunakan pendekatan Research and Development (R&D) dengan model pengembangan Waterfall yang meliputi analisis kebutuhan, perancangan, implementasi, dan pengujian sistem. Hasil penelitian berupa sistem pendukung keputusan yang membantu Ketua Program Studi menetapkan dosen pembimbing secara lebih objektif, merata, dan efisien, sekaligus memfasilitasi pengajuan judul skripsi secara elektronik. Sistem dikembangkan mengacu pada standar kualitas perangkat lunak ISO 25010 untuk memastikan aspek fungsionalitas dan keandalannya. Penelitian ini berkontribusi pada pengembangan sistem pendukung keputusan dalam layanan akademik perguruan tinggi melalui penerapan Profile Matching untuk penentuan dosen pembimbing skripsi yang lebih objektif dan terstruktur.
Pengembangan Media Pembelajaran IPA Berbasis Augmented Reality Menggunakan Unity Untuk Siswa Kelas VII Jihan Oktrio; Gusnita Darmawati; Yulifda Elin Yuspita; Firdaus Annas; Valentina Zahara
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1521

Abstract

Science instruction at MTsN 6 Lima Puluh Kota was still dominated by lectures and textbooks, resulting in students’ limited understanding of abstract scientific concepts. This study aimed to develop a Unity-based Augmented Reality (AR) learning medium and to examine its validity, practicality, and effectiveness in science learning. The study employed a Research and Development method using the ADDIE model, which consists of Analysis, Design, Development, Implementation, and Evaluation stages. The participants involved media experts, subject matter experts, teachers, and students. The results showed that the developed media achieved a validity score of 0.89, a practicality score of 0.92, and an effectiveness score of 0.90, all of which were categorized as very high. These findings indicate that the Unity-based AR learning media is feasible for use in science instruction and has the potential to support students’ understanding of abstract concepts. Abstrak Pembelajaran IPA di MTsN 6 Lima Puluh Kota masih didominasi metode ceramah dan penggunaan buku teks, yang menyebabkan rendahnya pemahaman siswa terhadap konsep-konsep abstrak. Penelitian ini bertujuan untuk mengembangkan media pembelajaran Augmented Reality (AR) berbasis Unity serta menilai validitas, praktikalitas, dan efektivitasnya dalam pembelajaran IPA. Penelitian ini menggunakan metode Research and Development dengan model ADDIE yang meliputi Analysis, Design, Development, Implementation, dan Evaluation. Subjek penelitian melibatkan ahli media, ahli materi, guru, dan siswa. Hasil penelitian menunjukkan bahwa media yang dikembangkan memperoleh skor validitas 0,89, praktikalitas 0,92, dan efektivitas 0,90, yang seluruhnya berada pada kategori sangat tinggi. Temuan ini menunjukkan bahwa media pembelajaran AR berbasis Unity layak digunakan dalam pembelajaran IPA dan berpotensi mendukung pemahaman siswa terhadap konsep-konsep abstrak.
Perancangan Aplikasi Pembelajaran Tata Cara Sholat Berbasis Android Untuk Meningkatkan Keterampilan Praktik Ibadah Siswa Efmi Maiyana; Wahyu Hidayat; Sadar Martua Haholongan Sir
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1634

Abstract

Technological advances in education provide opportunities to improve Islamic teaching, particularly in learning to read and practice prayer. MTsN 1 Bukittinggi experienced a problem, namely boredom among students due to the continued use of presentation slides and lecture-based teaching methods. Therefore, the researcher wanted to design a learning media application for prayer procedures. This study aims to design an Android-based application for learning prayer procedures as a medium to improve students' worship skills. The application was developed using the Research and Development (R&D) method with the ADDIE model, which includes needs analysis, design, development, implementation, and evaluation. The application design consisted of two stages, namely logical design using UML, which included use case diagrams, sequence diagrams, and activity diagrams, followed by physical design, where the application was developed using Android Studio and equipped with features such as prayer material, movement guides, audio recitations, and evaluations. The results of the black box media test showed that the application functioned properly. The designed learning media application provides features and supporting menus that offer practicality in using the learning media application for prayer procedures, such as the prayer menu, the Qur'an, and the determination of the qibla direction. Abstrak Pertumbuhan teknologi dalam bidang Pendidikan memberikan peluang untuk meningkatkan pembelajaran ajaran islam, khususnya dalam pembelajaran bacaan dan praktik sholat. Pada MTsN 1 Bukittinggi mengalami permasalahan yaitu rasa bosan yang timbul bagi siswa karena masih menggunakan media pembelajaran slide presentasi dengan metode ceramah sehingga peneliti ingin merancang sebuh aplikasi media pembelajaran tata cara sholat. Penelitian ini bertujuan merancang aplikasi pembelajaran tata cara salat berbasis Android sebagai media untuk meningkatkan keterampilan praktik ibadah siswa. Pengembangan aplikasi dilakukan dengan metode Research and Development (R&D) menggunakan model ADDIE yang meliputi analisis kebutuhan, perancangan, pengembangan, implementasi, dan evaluasi. Perancangan aplikasi terdiri dari dua tahapan yaitu perancangan secara logika menggunakan UML yang meliputi use case diagram, sequence diagram dan activity diagram, kemudian perancangan secara fisik dimana aplikasi dikembangkan menggunakan Android Studio dan dilengkapi fitur materi salat, panduan gerakan, audio bacaan, serta evaluasi. Hasil uji black box media menunjukkan bahwa aplikasi berfungsi dengan baik. Aplikasi media pembelajaran yang telah dirancang menghadirkan fitur dan menu – menu pendukung yang dapat memberikan kepraktisan dalam menggunakan aplikasi media pembelajaran tata cara sholat seperti menu do’a, Al – Qur’an dan penentuan arah kiblat.
Pemodelan dan Prediksi Curah Hujan Menggunakan SARIMA untuk Mendukung Perencanaan Irigasi Presisi di Kabupaten Temanggung Olivia Wardhani; Rheza Ari Wibowo; Ikhwan Alfath Nurul Fathony Fathony; Beta Estri Adiana; Yasabuana Athallahaufa Natawijaya; Rayfal Mayvandra Aurora Akbar
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1642

Abstract

Changes in rainfall patterns in tropical regions increase uncertainty in agricultural water management, particularly in rainfed areas such as Temanggung Regency, Indonesia. This condition highlights the need for data-driven rainfall prediction models to support precision irrigation planning and drought risk mitigation. This study aims to develop rainfall and rainday prediction models using the Seasonal Autoregressive Integrated Moving Average (SARIMA) method based on monthly climatological data for the period 2014–2024. The analysis follows the Box–Jenkins procedure, including seasonal pattern exploration, stationarity testing, parameter identification using ACF and PACF, parameter estimation, and diagnostic and accuracy evaluation. The results indicate that the SARIMA(0,0,1)(1,0,1,12) model provides the best performance for rainfall prediction, achieving an RMSE of 99.92 mm and an MAE of 57.84 mm, while rainday prediction exhibits relatively higher errors. The model successfully captures consistent annual seasonal patterns and generates projections for 2025, indicating higher rainfall at the beginning of the year and a significant decrease during the dry season. These findings provide a quantitative basis for developing water availability risk calendars and adjusting precision irrigation strategies at the regional level, supporting sustainable water resource management and regional food security. Abstrak Perubahan pola curah hujan di wilayah tropis meningkatkan ketidakpastian dalam pengelolaan air pertanian, terutama pada wilayah tadah hujan seperti Kabupaten Temanggung. Kondisi ini menuntut pemanfaatan model prediksi berbasis data sebagai landasan perencanaan irigasi presisi dan mitigasi risiko kekeringan. Penelitian ini bertujuan untuk membangun model prediksi curah hujan dan hari hujan menggunakan metode Seasonal Autoregressive Integrated Moving Average (SARIMA) berbasis data klimatologis bulanan periode 2014–2024. Analisis dilakukan menggunakan prosedur Box–Jenkins yang mencakup eksplorasi pola musiman dan pengujian stasioneritas. Tahapan selanjutnya meliputi identifikasi parameter melalui ACF dan PACF, estimasi parameter, serta evaluasi diagnostik residual dan akurasi model. Hasil pemodelan menunjukkan bahwa model SARIMA(0,0,1)(1,0,1,12) memberikan kinerja terbaik untuk prediksi curah hujan dengan nilai RMSE sebesar 99,92 mm dan MAE sebesar 57,84 mm, sedangkan prediksi hari hujan menghasilkan tingkat kesalahan yang relatif lebih tinggi. Model mampu merepresentasikan pola musiman tahunan secara konsisten dan menghasilkan proyeksi tahun 2025 yang menunjukkan curah hujan tertinggi pada awal tahun serta penurunan signifikan pada periode kemarau. Temuan ini memberikan landasan kuantitatif untuk penyusunan kalender risiko ketersediaan air dan penyesuaian strategi irigasi presisi pada skala regional, sehingga mendukung pengelolaan sumber daya air dan ketahanan pangan daerah.
AI-Driven Learning Analytics for Self-Regulated and Metacognitive Learning: A Systematic Review Rhezwan Dhaifullah Romdhoni; Rafli Arrasyid; Suprih Widodo; Ulva Elviani
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1657

Abstract

Artificial intelligence (AI) and learning analytics are increasingly integrated into educational systems, yet their impact on self‑regulated learning (SRL) and metacognition remains not fully understood. This systematic review synthesizes findings from 34 empirical and review studies on AI‑driven learning analytics in formal education, focusing on their effects on SRL, metacognition, motivation, and academic performance. Following PRISMA guidelines, studies were identified through searches in Scopus, Web of Science, ERIC, and Google Scholar for articles published between 2020 and 2025, using keywords related to AI, learning analytics, SRL, and metacognition. Studies were included if they used AI‑based analytical or adaptive systems, standardized SRL or metacognitive measures, and pre–post or comparison data. Results show that AI‑based tools such as predictive models, intelligent tutoring systems, adaptive platforms, learning dashboards, and generative or conversational AI support goal setting, monitoring, strategy adjustment, and reflective evaluation through feedback, progress visualization, and personalized recommendations. Most studies report improvements in SRL strategies, metacognitive awareness, motivation, engagement, and learning outcomes, though effects vary across research design quality, educational levels, and subject areas. However, several challenges persist, including infrastructural limitations, limited teacher readiness, data privacy and ethical issues, algorithmic bias, and potential overreliance on AI that may weaken learners’ independent strategic thinking. Overall, AI‑driven learning analytics hold substantial potential to enhance SRL and metacognition when integrated within coherent pedagogical frameworks and supported by institutional policies promoting transparency, equity, and human agency. Abstrak Kecerdasan buatan (AI) dan learning analytics semakin meluas dalam sistem pendidikan, namun dampaknya terhadap self‑regulated learning (SRL) dan metakognisi masih belum sepenuhnya dipahami. Tinjauan sistematis ini mensintesis temuan dari 34 studi empiris dan tinjauan pustaka mengenai penerapan AI‑driven learning analytics di pendidikan formal, berfokus pada pengaruhnya terhadap SRL, metakognisi, motivasi, dan kinerja akademik. Dengan mengikuti pedoman PRISMA, artikel dipilih melalui pencarian di Scopus, Web of Science, ERIC, dan Google Scholar untuk periode 2020–2025 menggunakan kata kunci terkait AI, learning analytics, SRL, dan metakognisi. Studi disertakan jika menggunakan sistem analitik atau adaptif berbasis AI dengan instrumen terstandar dan data perbandingan pre–post. Hasil menunjukkan bahwa alat berbasis AI seperti model prediktif, sistem tutor cerdas, platform adaptif, dashboard pembelajaran, serta AI generatif atau konversasional mendukung penetapan tujuan, pemantauan, adaptasi strategi, dan refleksi melalui umpan balik, visualisasi kemajuan, dan rekomendasi otomatis. Sebagian besar studi melaporkan peningkatan strategi SRL, kesadaran metakognitif, motivasi, keterlibatan, dan hasil belajar, meski efek berbeda bergantung pada desain penelitian, jenjang pendidikan, dan bidang studi. Namun, tantangan tetap muncul, termasuk keterbatasan infrastruktur, kesiapan guru, privasi data, bias algoritmik, serta potensi ketergantungan berlebih pada AI yang dapat melemahkan kemandirian berpikir strategis. Secara keseluruhan, AI‑driven learning analytics berpotensi memperkuat SRL dan metakognisi bila diintegrasikan dalam kerangka pedagogis yang jelas dan didukung kebijakan institusional yang menegakkan transparansi, keadilan, dan agensi manusia.
Analysis of Lifestyle Classification Using a Decision Tree Approach Afriosa Syawitri; Siti Rahmi Hidayatullah; Miranda Nuraini
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i02.1661

Abstract

Lifestyle related health issues continue to increase, highlighting the need for data-driven approaches that not only classify lifestyle patterns but also provide interpretable insights to support health-related decision making. This study aims to develop an interpretable lifestyle classification model using the Decision Tree algorithm, with a specific analytical focus on identifying dominant behavioral factors and their hierarchical relationships in distinguishing healthy and unhealthy lifestyles. The dataset was collected through a questionnaire survey involving 130 respondents representing diverse lifestyle behaviors. Initially, 23 attributes measured using Likert scales were used to capture multiple aspects of lifestyle. To improve analytical clarity and reduce data complexity, the attributes were transformed by grouping conceptually related items into four main behavioral domains: diet, physical activity, sleep patterns, and mental health. Personal demographic attributes were excluded from the modeling process due to their limited relevance to lifestyle behavior and their potential to introduce classification bias. Within each domain, sub-attributes were aggregated using mean values to generate stable composite scores, a methodologically appropriate approach given the non-parametric and threshold-based characteristics of the Decision Tree algorithm. The applied to reduce overfitting. The results indicate that the proposed model achieved an accuracy of 84.62% and a weighted average F1-score of 0.84, demonstrating balanced classification performance. The model showed strong recall in identifying healthy lifestyles, while limitations related to generalizability remain. Transformed dataset was divided into training and testing sets using a 70:30 hold-out validation strategy. Model construction employed the entropy criterion and information gain for attribute selection, with complexity control. Abstrak Masalah kesehatan terkait gaya hidup terus meningkat, menyoroti perlunya pendekatan berbasis data yang tidak hanya mengklasifikasikan pola gaya hidup tetapi juga memberikan wawasan yang dapat ditafsirkan untuk mendukung pengambilan keputusan terkait kesehatan. Penelitian ini bertujuan untuk mengembangkan model klasifikasi gaya hidup yang dapat diinterpretasikan menggunakan algoritma Decision Tree, dengan fokus analitis khusus untuk mengidentifikasi faktor perilaku dominan dan hubungan hierarkisnya dalam membedakan gaya hidup sehat dan tidak sehat. Kumpulan data dikumpulkan melalui survei kuesioner yang melibatkan 130 responden yang mewakili beragam perilaku gaya hidup. Awalnya, 23 atribut yang diukur menggunakan skala Likert digunakan untuk menangkap berbagai aspek gaya hidup. Untuk meningkatkan kejelasan analitis dan mengurangi kompleksitas data, atribut diubah dengan mengelompokkan item yang terkait secara konseptual menjadi empat domain perilaku utama: diet, aktivitas fisik, pola tidur, dan kesehatan mental. Atribut demografis pribadi dikecualikan dari proses pemodelan karena relevansinya yang terbatas dengan perilaku gaya hidup dan potensinya untuk memperkenalkan bias klasifikasi. Dalam setiap domain, sub-atribut dikumpulkan menggunakan nilai rata-rata untuk menghasilkan skor komposit yang stabil, pendekatan yang sesuai secara metodologis mengingat karakteristik non-parametrik dan berbasis ambang batas dari algoritma Pohon Keputusan. Himpunan data yang diubah dibagi menjadi set pelatihan dan pengujian menggunakan strategi validasi penahanan 70:30. Konstruksi model menggunakan kriteria entropi dan perolehan informasi untuk pemilihan atribut, dengan kontrol kompleksitas diterapkan untuk mengurangi overfitting. Hasil menunjukkan bahwa model yang diusulkan mencapai akurasi 84,62% dan skor F1 rata-rata tertimbang 0,84, menunjukkan kinerja klasifikasi yang seimbang. Model ini menunjukkan ingatan yang kuat dalam mengidentifikasi gaya hidup sehat, sementara keterbatasan yang terkait dengan generalisasi tetap ada.
Developing a Decision Support System for Assessing Bantara Rank Promotion Eligibility among Secondary School Scouts Wawan Fadhilah; Riri Okra; Hari Antoni Musril; Sarwo Derta
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 5 No. 01 (2026): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v5i01.1666

Abstract

Assessing student eligibility for Bantara rank promotion requires an objective and systematic decision-making process. This study aimed to develop a technology-based decision support system to assist scout supervisors in evaluating students’ eligibility for Bantara rank promotion at a secondary school. The system was developed using the Scrum framework within an Agile development approach, including product backlog preparation, sprint planning, sprint implementation, sprint review, and retrospective activities. The development process was conducted over six weeks, comprising 26 effective working days. The system applied the Weighted Scoring Model to calculate and determine students’ promotion eligibility. The evaluation results showed a validity score of 0.97, a practicality score of 0.615, and an average effectiveness score of 0.93. These findings indicate that the developed system met the evaluation criteria used in the study and was considered feasible for supporting Bantara promotion assessments. The system provides a more structured basis for decision-making and may assist scout supervisors in conducting student assessments more consistently and objectively. Abstrak Penilaian kelayakan siswa untuk kenaikan pangkat Bantara memerlukan proses pengambilan keputusan yang objektif dan sistematis. Penelitian ini bertujuan untuk mengembangkan sistem pendukung keputusan berbasis teknologi guna membantu pembina pramuka dalam mengevaluasi kelayakan siswa untuk kenaikan pangkat Bantara di sebuah sekolah menengah. Sistem ini dikembangkan menggunakan kerangka kerja Scrum dalam pendekatan pengembangan Agile, yang mencakup persiapan product backlog, perencanaan sprint, pelaksanaan sprint, tinjauan sprint, dan kegiatan retrospektif. Proses pengembangan berlangsung selama enam minggu, yang terdiri dari 26 hari kerja efektif. Sistem ini menerapkan Model Penilaian Berbobot untuk menghitung dan menentukan kelayakan siswa dalam promosi. Hasil evaluasi menunjukkan skor validitas sebesar 0,97, skor kepraktisan sebesar 0,615, dan skor efektivitas rata-rata sebesar 0,93. Temuan ini menunjukkan bahwa sistem yang dikembangkan memenuhi kriteria evaluasi yang digunakan dalam penelitian ini dan dianggap layak untuk mendukung penilaian promosi Bantara. Sistem ini menyediakan landasan yang lebih terstruktur untuk pengambilan keputusan dan dapat membantu pembina pramuka dalam melakukan penilaian siswa secara lebih konsisten dan objektif.

Page 11 of 11 | Total Record : 110

 7   8   9   10   11 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 01 (2026): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 02 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 1 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 3 No. 2 (2024): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 3 No. 1 (2024): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 2 No. 2 (2023): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 2 No. 1 (2023): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 1 No. 2 (2022): Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 1 No. 1 (2022): Intellect : Indonesian Journal of Learning and Technological Innovation