Claim Missing Document
Check
Articles

Found 37 Documents
Search

Boundless Creativity: Vlogging with a Smartphone in the Digital Era Kala'lembang, Adriani; Riska, Suastika Yulia; Widayanti, Lilis; Rahayu, Widya Adhariyanty; Fitria, Vivi Aida
Jurnal Pengabdian Masyarakat Vol. 6 No. 1 (2025): Jurnal Pengabdian Masyarakat
Publisher : Institut Teknologi dan Bisnis Asia Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jpm.v6i1.2475

Abstract

Purpose: This community service aims to enhance the technical skills of students at SMK Negeri 12 Malang in digital vlog creation. Method: The program involves training sessions using lectures and hands-on practice to improve lighting techniques. Practical Application: This initiative has a significant impact on vlog production by following essential steps, including framing techniques, lighting, and video editing. Conclusion: This program enhances students' creativity and skills in vlog creation.
High-accuracy classification of banana varieties using ResNet-50 and DenseNet-121 architectures Riska, Suastika Yulia; Sulistyo, Danang Arbian; Siti Maharani, Farah Shafiyah
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 1: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i1.pp322-335

Abstract

Bananas are a popular fruit in Indonesia due to their affordability, availability, and rich nutritional content. Identifying different banana types is crucial for consumption and processing, yet some types are difficult to distinguish visually. This study aims to classify banana types using convolutional neural network (CNN) architectures, specifically ResNet-50 and DenseNet-121. The dataset consists of five banana classes, which were processed using preprocessing techniques to enhance image quality prior to model training. The results demonstrate that the proposed models can classify banana types with high accuracy. The research methodology includes data collection, preprocessing, CNN model implementation, and performance evaluation using a confusion matrix. The dataset was split into training and testing sets in an 80:20 ratio, with validation data extracted from the training set in a 90:10 ratio. The models were trained on the training data, validated with validation data, and tested on the testing data to assess final performance. The study concludes that the CNN architectures employed are effective in classifying banana types, with the DenseNet-121 model achieving 93.02% accuracy, outperforming the ResNet-50 model, which achieved 92.44%. These results indicate that the models can capture essential features from banana images and produce accurate predictions.
Early Detection of Student Problems Through a Knowledge-Based Systems-Based Counseling Approach Rahmawati, Nisrina Salsabil; Riska, Suastika Yulia
Journal of Information Technology and Cyber Security Vol. 3 No. 1 (2025): January
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.12617

Abstract

Higher education is an important phase in an individual's academic development, but it is often characterized by challenges such as academic pressure, time management, and student mental health. To overcome these problems, this research aims to develop a technology-based Counseling Expert System with a Forward Chaining approach to detect student problems and provide relevant solutions. The system is designed and implemented as a web-based platform that can be accessed anytime and anywhere, allowing students to answer questions related to the problems faced by students. The answers are processed in a knowledge base that is integrated with an inference engine to produce diagnosis and solution recommendations. The results of system testing using 30 data samples show results that are in accordance with expert judgment. This expert system can identify six types of student problems, such as laziness, skipping classes, adaptation difficulties, difficulty doing final assignments, decreased Grade Point Average (GPA or IP), and potential dropout, by considering 32 causal factors grouped into academic, time management, emotional, and social environment categories. This research proves that the Forward Chaining-based Counseling Expert System is effective as a flexible solution to support student well-being and better student academic achievement.
Penguatan Nasionalisme pada Era Digital melalui Game Mobile Edukatif Bilingual bagi Siswa Inklusif Muslim, Abdul Aziz; Rahayu, Widya Adhariyanty; Riska, Suastika Yulia
Jurnal Masyarakat Madani Indonesia Vol. 4 No. 4 (2025): November
Publisher : Alesha Media Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59025/b3rdg674

Abstract

SD Muhammadiyah 4 Kota Malang sebagai lembaga pendidikan berbasis inklusif menghadapi tantangan signifikan dalam pelaksanaan pembelajaran, terutama dengan pendekatan konvensional yang kurang adaptif bagi siswa slow learner. Untuk mengatasi permasalahan tersebut, diusulkan inovasi berupa pengembangan media pembelajaran digital melalui game mobile edukatif bilingual bertema nasionalisme. Kegiatan ini bertujuan memperkuat wawasan kebangsaan sekaligus meningkatkan keterampilan bahasa Inggris siswa inklusif. Metode pelaksanaan menerapkan pendekatan berbasis komunitas yang melibatkan guru, orang tua, dan pakar pendidikan dalam tahapan identifikasi kebutuhan, perancangan hingga implementasi serta evaluasi game interaktif. Pelatihan bagi guru dan sosialisasi untuk orang tua turut diberikan guna memastikan optimalisasi pemanfaatan media baru ini di sekolah dan di rumah. Hasil kegiatan menunjukkan game “Nusantaraku” dapat meningkatkan motivasi belajar, pemahaman konsep nasionalisme, dan keterampilan bahasa Inggris, yang tercermin dari partisipasi aktif siswa, respon positif guru dan orang tua, serta kenaikan hasil evaluasi belajar. Kendala utama berupa keterbatasan perangkat digital dan kebutuhan pelatihan lanjutan bagi guru, namun secara umum kegiatan berhasil membawa perubahan nyata dalam proses pembelajaran yang lebih inklusif, menyenangkan, serta mendorong partisipasi seluruh pihak sekolah.
Early Stroke Disease Prediction Based on Lifestyle Factors Applied with Machine Learning Suastika Yulia Riska; Lia Farokhah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 5 (2025): October 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i5.6495

Abstract

Stroke prediction has many supporting features and variables. Some forecasts focus more on health or elements that are already present. Predicting stroke risk by identifying habitual factors provides more advantages for preventive action. In addition, the complexity of features or variables is a concern in predicting stroke risk. In this study, we used a public dataset from Kaggle with 10 features or variables. In this study, we propose to collaborate algorithms and preprocessing in feature selection using Pearson Correlation and Principal Component Analysis (PCA) dimension reduction to unravel the complexity of variables and data processing computing. This aims to predict stroke risk more simply. The results of the experiment show that feature selection using Pearson Correlation between features and labels produces maximum results using 5 features out of 10 provided features. This approach produces the best performance on the Naïve Bayes, Iterative Dichotomiser Tree (ID3), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Logistic Regression with 100% accuracy and reduces features by 50% to support the reduction of the complexity of prediction variables and data processing computing.
Ontology-Based Recommender Systems for E-Learning and Multimedia: A Systematic Literature Review Across Domains Riska, Suastika Yulia; Patmanthara, Syaad; Widiyaningtyas, Triyanna
Indonesian Journal of Instructional Media and Model Vol 7 No 2 (2025): Indonesian Journal of Instructional Media and Model
Publisher : Universitas Veteran Bangun Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32585/ijimm.v7i2.7405

Abstract

The rapid expansion of digital content across various sectors has led to an overwhelming influx of data, highlighting the need for advanced recommendation systems. Traditional methods such as Collaborative Filtering (CF) and Content-Based Filtering (CBF) face limitations like data sparsity and the Cold Start problem, which affect the accuracy of recommendations. This study explores the use of ontologies in enhancing recommendation systems, aiming to overcome these challenges by providing a semantic framework for better item and user representation. A Systematic Literature Review (SLR) methodology was employed to analyze research from 2021 to 2025, focusing on the application of ontologies in e-commerce, healthcare, education, and employment. The findings demonstrate that ontologies improve recommendation relevance, diversity, and explainability, especially in addressing the Cold Start problem. However, challenges in implementation and interpretation remain. This research contributes to the field by emphasizing the potential of integrating ontologies with Knowledge Graphs (KG) and Graph Neural Networks (GNN) to create hybrid models that enhance the accuracy and transparency of recommendations, guiding future advancements in recommendation systems.
Language Diplomacy Through BIPA: An Indonesian Language Training Program For NEUST Philippines Students Lailatul Aqromi, Nur; Yulia Riska, Suastika; T. Bantug, Emilsa; Febrindasari, Chyndy
International Journal Of Community Service Vol. 5 No. 4 (2025): November 2025 ( Indonesia - Thailand - Malaysia - Timor Leste - Philippines )
Publisher : CV. Inara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51601/ijcs.v5i4.930

Abstract

This community engagement program was initiated in response to the linguistic needs of foreign students from the Nueva Ecija University of Science and Technology (NEUST), Philippines, who required Indonesian language proficiency to participate effectively in a student exchange program with the Institute of Technology and Business Asia Malang, Indonesia. The partner institution faced two primary challenges: the absence of a practical and systematic Indonesian language training program for foreign learners and the limited initial language competence among NEUST students. Interestingly, structural similarities between Tagalog and Indonesian—particularly in basic morphemes and affixation patterns—offered a promising foundation for language acquisition. The program aimed to introduce fundamental Indonesian language proficiency equivalent to BIPA Level 4, focusing on communicative competence in academic and social contexts. It was conducted online through five sessions, including one orientation, four core training sessions based on the Task-Based Language Teaching (TBLT) approach, and one evaluation session. The learning materials were adapted from Sahabatku Indonesia – BIPA 4, published by the Ministry of Education and Culture. The outcomes demonstrated significant improvement in participants’ linguistic competence, reflected in higher evaluation scores and active engagement throughout the training. Additional outcomes included online media publications and the adoption of the developed modules as sustainable BIPA teaching materials at NEUST. Overall, this initiative represents an effort in Indonesian language diplomacy, contributing to the strengthening of academic mobility and intercultural collaboration across Southeast Asia.