Claim Missing Document
Check
Articles

Pengendalian Gerak Robot Beroda Menggunakan Sarung Tangan Pintar dengan Neural Network Backpropagation Arif, Yunifa Miftachul; Mustofa, Ahmad Habibil; Holle, Khadijah Fahmi Hayati; Wibowo, Muhammad Ismail Arjun; Aziza, Miladina Rizka; Junikhah, Allin; Hasanah, Novrindah Alvi
SinarFe7 Vol. 7 No. 1 (2025): SinarFe7-7 2025
Publisher : FORTEI Regional VII Jawa Timur

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

Abstract

Pengendalian robot berbasis remote control konvensional kerap memerlukan adaptasi dan pembelajaran baru bagi pengguna, khususnya bagi mereka yang belum terbiasa dengan tata letak tombol yang kompleks. Penelitian ini menawarkan solusi yang lebih intuitif melalui pendekatan Hand Gesture Recognition berbasis sarung tangan pintar (smart glove) yang dilengkapi sensor MEMS berupa akselerometer dan giroskop. Data pergerakan tangan yang diperoleh diolah menggunakan metode Neural Network Backpropagation untuk mengenali lima jenis gerakan, yaitu diam, maju, mundur, belok kiri, dan belok kanan. Sistem dikembangkan pada mikrokontroler STM32F10C dengan modul nirkabel NRF24L01 sebagai media transmisi data ke robot beroda. Pengujian dilakukan oleh satu orang pengguna dengan sepuluh kali percobaan untuk setiap gerakan. Hasil klasifikasi menunjukkan tingkat akurasi rata-rata sebesar 82,8%, dengan respon yang cepat dan stabil terhadap perintah yang diberikan. Temuan ini membuktikan bahwa pengendalian robot dapat dilakukan secara lebih natural, efisien, dan responsif hanya dengan gerakan tangan, sehingga berpotensi dikembangkan untuk aplikasi yang lebih luas di masa depan.
Extended reality for education: Mapping current trends, challenges, and applications Samala, Agariadne Dwinggo; Bojic, Ljubisa; Rawas, Soha; Howard, Natalie-Jane; Arif, Yunifa Miftachul; Tsoy, Dana; Coelho, Diogo Pereira
Jurnal Pendidikan Teknologi Kejuruan Vol 7 No 3 (2024): Regular Issue
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jptk.v7i3.37623

Abstract

The advancements in 5G technology and Artificial Intelligence (AI) have accelerated the integration of immersive technologies such as Extended Reality (XR) into educational practices. There is a notable scarcity of studies focusing specifically on the applications and impact of XR in academic settings. Most existing research has concentrated on AR and VR, leaving a gap in understanding the full potential of XR. Addressing these gaps and challenges is crucial for harnessing the full potential of XR in education. This study aims to map and analyze the applications, trends, and educational challenges of XR technology. This study conducts a bibliometric analysis covering XR's application in education from 2018 to 2023, analyzing 32 articles from Scopus sources. Key findings highlight XR's annual growth in research publications, with significant contributions from the United States, China, and Canada. XR enriches education by facilitating immersive simulations, real time interaction with virtual objects, and spatial manipulation in three dimensions. It fosters presence and embodiment in virtual environments, supports practical training through realistic simulations, enhances multi-sensory engagement, promotes collaborative learning environments, and improves accessibility for diverse learners. The main challenges of XR technology include high costs, technical hurdles, regulatory issues, infrastructure limitations, and the need for digital literacy and skills. Addressing these challenges, collaborative efforts among educators, researchers, and industry stakeholders are required. Such collaboration is crucial for harnessing the full potential of XR technology to revolutionize education and prepare learners for a dynamic future.
Comparative Analysis of Artificial Neural Networks, Linear Regression, Random Forest, and Support Vector Machine for Predicting Poverty Levels in Indonesia Alfia, Lia Alfia; Nugroho, Fresy; Arif, Yunifa Miftachul
International Journal of Advances in Data and Information Systems Vol. 6 No. 3 (2025): December 2025 - International Journal of Advances in Data and Information Syste
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v6i3.1467

Abstract

Poverty remains a persistent and complex challenge in Indonesia, driven by multiple interrelated socioeconomic factors. Accurate poverty prediction is essential to support effective policy formulation and targeted interventions. This study evaluates and compares the performance of four machine learning models for predicting poverty levels in Indonesia: Artificial Neural Networks (ANN), Linear Regression, Random Forest, and Support Vector Machine (SVM). A quantitative approach is employed using provincial-level data from 2015 to 2023, consisting of 306 observations and 13 socioeconomic indicators related to education, employment, health, infrastructure, and economic conditions. Data preprocessing includes data cleaning, Min–Max normalization, and feature selection. Model performance is assessed using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The results show that ANN achieves the best predictive performance, with the lowest MSE (0.0132) and MAE (0.0815), and the highest R² value (0.924). Random Forest and SVM demonstrate competitive performance, while Linear Regression yields the weakest accuracy. These findings confirm the effectiveness of ANN for poverty prediction and support its use in data-driven poverty reduction policies in Indonesia.
Sistem Rekomendasi Destinasi Wisata Menggunakan Data Demografis Berbasis Klasifikasi Support Vector Machine A'yun, Aldilla Qurrata; Arif, Yunifa Miftachul; ., Muhammad Imamudin
ILKOMNIKA Vol 7 No 3 (2025): Volume 7, Number 3, December 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28926/ilkomnika.v7i3.826

Abstract

Penelitian ini bertujuan untuk mengembangkan sistem rekomendasi destinasi wisata berbasis data demografis menggunakan metode klasifikasi Support Vector Machine (SVM). Sistem dirancang untuk memberikan rekomendasi destinasi yang sesuai dengan karakteristik wisatawan, seperti usia, jenis kelamin, dan status sosial. Dataset yang digunakan terdiri dari sepuluh variabel demografis dan empat belas kategori destinasi wisata. Analisis awal menunjukkan bahwa dataset memiliki ketidakseimbangan kelas yang sangat tinggi, dengan kelas Jatim Park 1 mendominasi lebih dari separuh data sementara banyak kelas lain hanya memiliki 1–6 sampel. Untuk mengurangi dampak ketidakseimbangan ini, dilakukan teknik oversampling pada data training. Model SVM kemudian dilatih menggunakan beberapa kombinasi parameter dan kernel, serta diuji menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil eksperimen menunjukkan bahwa pada data training yang sudah diseimbangkan, performa model meningkat signifikan, ditunjukkan oleh nilai F1-macro pada cross-validation sebesar 0.84. Namun, ketika diuji pada data testing yang mencerminkan kondisi distribusi asli, performa model menurun, dengan akurasi sebesar 54% dan nilai F1-macro yang rendah pada sebagian besar kelas minoritas. Temuan ini menunjukkan bahwa meskipun SVM efektif pada data yang seimbang, performanya masih belum optimal pada dataset rekomendasi wisata yang sangat timpang. Penelitian ini merekomendasikan pengayaan data, terutama untuk kelas-kelas minoritas, serta eksplorasi metode penanganan ketidakseimbangan kelas lainnya pada penelitian lanjutan.
DIGITAL DA'WAH AND THE RECONSTRUCTION OF ISLAMIC AUTHORITY A’lan Tabaika, Mokhammad; Barizi, Ahmad; Arif, Yunifa Miftachul
al-Balagh : Jurnal Dakwah dan Komunikasi Vol. 10 No. 2 (2025): December 2025
Publisher : Fakultas Ushuluddin dan Dakwah UIN Raden Mas Said Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22515/albalagh.v10i2.12116

Abstract

This study addresses the research gap regarding how Islamic authority is contested and reconstructed in the era of digital media, where social media dynamics disrupt traditional hierarchies. It aims to analyze how online Islamic preaching is transformed by social media logics, aesthetic strategies, and audience engagement, emphasizing the participatory and dialogical nature of comment sections. This research adopts a qualitative design using a netnographic approach, observing and analyzing social media content produced by prominent Indonesian Islamic figures, including Hanan Attaki, Abdul Somad, and Habib Husein Ja’far. The dataset comprises YouTube sermons, Instagram posts, TikTok videos, and user interactions, including comments and shares. Findings reveal the emergence of "religious influencers" who blend piety with branding, the commodification of Islamic preaching, and the evolution of comment sections into semi-public arenas of theological debate and negotiation. These interactions show how authority is no longer solely institutional but co-produced with audiences in real time. This study demonstrates that digital da’wah democratizes access to religious discourse while raising concerns about theological integrity, commercialization, and regulation challenges. It argues that understanding these dynamics is essential for developing critical digital religious literacy and fostering more inclusive, reflective, and ethically grounded online Islamic communication.
Deepfake Image Detection Using Transfer Learning Method Tsalatsatun Nur Rohmah; Dewi Purnamasari; Kurniawati Kurniawati; Didin Herlinudinkhaji; Yunifa Miftachul Arif; Santiago Criollo-C
International Journal of Electrical and Intelligent Engineering Vol 1, No 2 (2025)
Publisher : Department of Electrical Engineering Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/ijeie.v1i2.40796

Abstract

The development of Artificial Intelligence (AI) technologies, particularly deep learning has led to the emergence of innovative applications such as deepfake technology, which enables the realistic manipulation of digital images and videos. While this technology offers positive applications in fields such as entertainment and education, it also poses significant risks of misuse, particularly in the dissemination of false information and violations of privacy. Therefore, deepfake detection has become a crucial aspect in preserving the authenticity of digital content. This study aims to analyze the effectiveness of transfer learning methods in detecting deepfake images using VGG16, VGG19, and ResNet50 architectures. The research employs a dataset of deepfake and real images sourced from Kaggle, comprising 10,826 facial images with a resolution of 256 × 256 pixels, evenly balanced between authentic and manipulated content. The data are split in an 80:20 ratio for training and testing purposes. Each model is trained using identical parameter configurations. The performance evaluation of the models was conducted using confusion matrix metrics, including accuracy, precision, recall, and F1-score. The results indicate that the VGG16 model achieved the best performance, with an accuracy of 76%, followed by VGG19 at 72%, and ResNet50 at 58%. VGG16 also outperformed the other models in terms of precision, recall, and F1-score, demonstrating more effective performance in identifying visual manipulation patterns. In contrast, ResNet50 exhibited the lowest performance, which may be attributed to its architectural complexity not being optimally aligned with the characteristics of the dataset. It can be concluded that the transfer learning approach using the VGG16 model is more effective in detecting deepfake images on this dataset. This study also highlights the importance of selecting appropriate architectures and fine-tuning models to the characteristics of the data.
Ball Detection in Wheeled Soccer Robot Using the YOLOv8 Model Aqza Tri Ananda HAT; Shoffin Nahwa Utama; M. Imamudin; Yunifa Miftachul Arif; Ajib Hanani
International Journal of Electrical and Intelligent Engineering Vol 1, No 2 (2025)
Publisher : Department of Electrical Engineering Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/ijeie.v1i2.39317

Abstract

This research designs and builds a wheeled soccer robot using YOLOv8 for real-time ball detection and distance estimation, aiming to improve efficiency in technology competitions. The system includes Arduino Uno R3, Raspberry Pi 3 model b, detection system, and navigation design. 691 ball image use as dataset that consist of 552 image as training dataset and 249 image as valid dataset. YOLOv8 demonstrated exceptional reliability in ball detection during testing, achieving an average accuracy of 100%, 100% precision, and 94% recall. Navigation testing toward the ball had an acceptable average error of 8.0466%. The results confirm that YOLOv8 is excellent for simplifying high-accuracy ball detection and distance estimation in wheeled soccer robots. Future work should consider a higher-spec Raspberry Pi, a high-resolution camera, additional sensors, and advanced systems to improve detection and obstacle avoidance (opponent robots, goal).
Career Path Mapping Using the Random Forest Method for Vocational High School Graduates Imami, Nia Kurniawati; Hariyadi, Mokhamad Amin; Arif, Yunifa Miftachul
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 4 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i4.9297

Abstract

Vocational high school students are prepared to enter the labor market. However, field facts show that many graduates work outside their field of expertise. To address this, the special job placement bureau (Bursa Kerja Khusus/BKK) plays an important role as it connects graduates with industry. In addition, BKK provides pre-employment training such as interview preparation and soft-skill development. This study aims to develop a classification-based career-path mapping system integrated with BKK functions. The data used are scores of eight competency dimensions for vocational students obtained from BKK. The method employed is the Random Forest algorithm. We conduct hyperparameter tuning with cross-validation. Results show Random Forest achieves accuracy of 0.895 and an F1 score of 0.905. These results indicate that optimizing for F1 yields the best balance between precision and recall while maintaining high overall accuracy. Overall, this study confirms a trade-off between overall accuracy and inter-class balance (F1): constrained tree depth tends to maximize accuracy, whereas unconstrained depth benefits F1. Random Forest proves reliable and stable for the classification task in this career-path mapping
Performance of Multi-Criteria Recommender System Using Cosine-Based Similarity for Selecting Halal Tourism Rizqi Aulia Nadhifah; Yunifa Miftachul Arif; Hani Nurhayati; Linda Salma Angreani
Applied Information System and Management (AISM) Vol. 5 No. 2 (2022): Applied Information System and Management (AISM)
Publisher : Depart. of Information Systems, FST, UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/aism.v5i2.25035

Abstract

Tourism is an activity where people or groups travel voluntarily for relaxation, seeking entertainment, or enjoy cultural diversity both within the city, outside the city, or even abroad. For traveling, information about halal tourism is essential that tourists must know. Tourists can contact a tour guide to find information and recommendations for halal tourism. However, it will cost quite a bit and need for a recommendation system to obtain recommendations and make it easier for tourists to determine which halal tourism to visit. This study aims to obtain the Multi-Criteria Recommender System's (MCRS) performance using cosine-based similarity to select halal tourism in Batu City. MCRS extends the traditional approach by using more than one scoring criteria to generate recommendations. The implementation of MCRS using cosine-based similarity succeeded in producing the five highest recommendations for halal tourist attractions, which were implemented in a game-based system. Through recommendation accuracy testing on two items, three items, four items, and five tourist attractions items, we obtained an average accuracy is 77,95%.
Selecting Tourism Site Using 6 As Tourism Destinations Framework Based Multi-Criteria Recommender System Yunifa Miftachul Arif; Duvan Deswantara Putra; Nauman Khan
Applied Information System and Management (AISM) Vol. 6 No. 1 (2023): Applied Information System and Management (AISM)
Publisher : Depart. of Information Systems, FST, UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/aism.v6i1.25140

Abstract

Batu City is a place with many types of tourism and had many tourists in 2019. However, there was an imbalance of tourist attractions visited from the total number. Tourists are only fixated on famous tourist spots. Therefore, a recommendation system is needed that can provide recommendations for tourists. In this study, we use the Multi-Criteria Recommender System (MCRS) method based on the rating value between users to obtain recommendations from the system regarding selecting tourist destinations. The authors use the 6 As Tourism Destinations (6AsTD) framework for user assessment criteria in this study. The framework consists of six indicators that assess the success of tourism destinations, including attractions, accessibility, amenities, support services, activities, and available packages. The six components are considered the key to the success of a tourist destination under the marketing approach. This study aimed to obtain a recommendation system for selecting tourist destinations using the multi-criteria concept based on the 6AsTD framework. Based on the experimental results, the proposed method has an accuracy rate of up to 72%.
Co-Authors ., Muhammad Imamudin A'yun, Aldilla Qurrata AA Sudharmawan, AA Achmad Sabar, Achmad Ady Wicaksono Agariadne Dwinggo Samala Ahmad Barizi Ahmad Fahmi Karami Ajib Hanani Alfachruddin, M. Nabil Fahd Alfia, Lia Alfia Aqza Tri Ananda HAT Aristantia, Yuliana Aziza, Miladina Rizka A’lan Tabaika, Mokhammad Bojic, Ljubisa Cahyo Crysdian Coelho, Diogo Pereira Dedy Kurnia Setiawan Dewi Purnamasari Didin Herlinudinkhaji, Didin Dony Darmawan Putra Duvan Deswantara Putra Dyah Wardani Fachrul Kurniawan Fathir Fathir Fathir Fathurrahman Firmansyah, Rezky Fresy Nugroho Fresy Nugroho Hamid, Abdulhalim Hamid Salih Hani Nurhayati Howard, Natalie-Jane Ihsan, Afif Nuril Ikhlayel, Mohammed Imam Ashar Imami, Nia Kurniawati Imamudin, M Imamudin, M. Janitra, Geovanni Azam Juniardi Nur Fadila Junikhah, Allin Khadijah Fahmi Hayati Holle Kurniawati Kurniawati Linda Salma Angreani M. Imamudin Mauludiah, Siska Farizah Mauridhi H Purnomo Mochamad Hariadi Mochammad Wahyu Firmansyah Mokhamad Amin Hariyadi Muhammad Faisal Muhammad Faisal Muhammad Sahi Mustofa, Ahmad Habibil Nauman Khan Norizan Mat Diah Novrindah Alvi Hasanah Nurdin Wibisono Nursih Dwi Hastuti Putra, Dony Darmawan Rawas, Soha Ririen Kusumawati Rizqi Aulia Nadhifah Rohma, Salma Ainur Rony, Zahara Tussoleha Roro Inda Melani Safitri A Basid, Puspa Miladin Nuraida Santiago Criollo-C Shoffin Nahwa Utama Siska Farizah Mauludiah Suko Wiyanto Sulika Sulika Supeno Mardi S. N, Supeno Mardi Supeno Mardi Susiki Nugroho, Supeno Mardi Supriyono Tarranita Kusumadewi Tsalatsatun Nur Rohmah Tsoy, Dana Wahyudi, M Rizal Wahyuliningtyas, Lia Wibowo, Muhammad Ismail Arjun Zainal Abidin Zulfiandri Zulfiandri