cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Hasanuddin
Contact Email
cvraskhamediagroup@gmail.com
Phone
+6282362440765
Journal Mail Official
ikosstemi@gmail.com
Editorial Address
Jalan Gurilla No. 2 Sidorejo, Kec. Medan Tembung 20222
Location
Kota medan,
Sumatera utara
INDONESIA
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik Dan Multi-disiplin Ilmu
Published by CV. Raskha Media Group
ISSN : -     EISSN : 31232574     DOI : https://doi.org/10.64803/ikosstemi
Core Subject : Religion, Humanities, Science, Education, Engineering,
Religion Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu (IKOSSTEMI) dengen No. ISSN: 3123-2574 (online) merupakan salah satu kegiatan yang diselenggarakan oleh Raskha Media Group Publisher. Seminar Nasional IKOSSTEMI (Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu) dilaksanakan untuk memberikan dorongan kepada para Dosen, Mahasiswa, dan Penelitidalam melakukan publikasi di Forum Ilmiah Nasional dengan harapan manfaatnya dapat segera dirasakan masyarakat secara luas.
Arjuna Subject : Umum - Umum
Articles 6 Documents
 1 
Search results for , issue "vol. 2 (2026)" : 6 Documents clear
Pergeseran Otoritas Guru di Tengah Maraknya Bimbingan Belajar Arditya Prayogi; Lilik Riandita; Bagas Mukti Nasrowi; Riki Nasrullah
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.146

Abstract

Fenomena bimbingan belajar dalam lanskap pendidikan kontemporer tidak lagi dipandang hanya sebagai layanan tambahan di luar sekolah. Dalam banyak konteks, bimbingan belajar bergerak mengikuti sistem persekolahan formal, terutama dalam hal mata pelajaran, target akademik, dan orientasi evaluasi. Artikel ini bertujuan menelaah bagaimana kaitan antara maraknya bimbingan belajar dan pergeseran otoritas pedagogik guru di sekolah. Penelitian ini menggunakan pendekatan kualitatif berbasis literature review dengan menelaah berbagai pustaka yang relevan yang diperoleh melalui berbagai sumber/basis literatur. Hasil kajian menunjukkan bahwa bimbingan belajar tidak hanya berfungsi sebagai pendamping akademik, tetapi juga menjadi ruang belajar yang semakin dipercaya siswa karena dianggap lebih praktis, komunikatif, dan responsif terhadap kebutuhan ujian. Kondisi ini mendorong terjadinya pergeseran pusat kepercayaan belajar dari guru kepada tutor, meskipun guru tetap memiliki legitimasi formal di sekolah. Pergeseran tersebut dipengaruhi oleh budaya pendidikan yang berorientasi hasil, keterbatasan pembelajaran di kelas, serta meningkatnya ekspektasi orang tua terhadap capaian akademik.
Implementation of Federated Learning for Disease Classification with Imbalanced Dataset Syarifah Yusnaini Putri; Nia Ramadani; Andre Hasudungan Lubis
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.148

Abstract

Imbalanced data is one of the main challenges in applying machine learning to stroke disease classification, where the number of stroke patient data is significantly smaller than non-stroke patient data. This condition causes classification models to become biased toward the majority class, resulting in poor detection of stroke cases. In addition, centralized learning approaches raise privacy and security concerns due to the sensitive nature of patient data. Therefore, this study proposes a Federated Learning Random Forest (FL-RF) approach to improve classification performance on imbalanced data while preserving data privacy. The study uses the Cerebral Stroke Prediction – Imbalanced Dataset obtained from Kaggle. The research stages include data preprocessing, semi non-IID data distribution across multiple clients, local training using Balanced Random Forest, and model aggregation within a federated learning environment. Model evaluation was conducted using accuracy, precision, recall, F1-score, confusion matrix, and ROC curve metrics. The results show that the conventional Random Forest achieved an accuracy of 0.9817 but failed to detect the minority class. Meanwhile, the proposed FL-RF model obtained an accuracy of 0.7976 with an improved recall of 0.56 and an F1-score of 0.0910 for the stroke class. These findings indicate that the FL-RF approach is more effective in improving sensitivity toward minority classes compared to conventional Random Forest.  
Interactive AR Book Learning Media for Introducing Animal Types Based on Augmented Reality for Early Childhood Farhan Fadhel Muhammad; Saiba Anjeli; Yuke Try Hafsani; Yoyon Efendi; Nurul Utami
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.149

Abstract

Augmented Reality (AR) is a technology that can display two-dimensional (2D) and three-dimensional (3D) virtual objects in real time through smartphone screens or other digital devices. In its application, AR technology utilizes markers in the form of certain images or images to display 3D objects that have been designed on the system. The implementation of Augmented Reality is currently widely used in various fields, one of which is in the field of education as an interactive learning medium for early childhood. The problem that is often found in the learning process is the use of learning media that is still conventional so that children easily feel bored and less interested when getting to know the type of animal. This research aims to design an interactive learning media AR Book to recognize animal types based on Augmented Reality in early childhood using Assemblr Studio. The research method used is Research and Development (R&D) with the ADDIE development model which consists of the analysis, design, development, implementation, and evaluation stages. The types of animals used include land, sea, and air animals that are displayed in the form of three-dimensional objects (3D) through the process of scanning markers using a smartphone. Learning media is also equipped with information on animal characteristics so that it helps children understand the material more interestingly and interactively. Research results show that Augmented Reality-based AR Book learning media can be used well as a learning tool and help increase early childhood learning interest in recognizing animal species.
UI/UX Design of ”Cari Kos PKU” Application Using Design Thinking Method Anton Afandi; Fahriel Abdul Rasyid; Nurva Fitri Andini; Salsabila Sahbani; Yoyon Efendi; Tashid Tashid
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.150

Abstract

Mahasiswa dan karyawan sering menghadapi kesulitan dalam mencari kos yang sesuai dengan kriteria seperti lokasi, harga, dan fasilitas. Proses pencarian yang tidak efisien dan memakan waktu menjadi hambatan utama. Penelitian ini bertujuan merancang antarmuka pengguna (UI/UX) aplikasi Cari Kos PKU sebagai solusi digital pencarian kos di Kota Pekanbaru yang mudah digunakan dan sesuai kebutuhan pengguna. Metode yang digunakan adalah Design Thinking dengan tahapan: Empathize, Define, Ideate, Prototype, dan Test. Perancangan prototipe dilakukan menggunakan aplikasi Figma dalam bentuk desain low-fidelity dan high-fidelity. Pengujian menggunakan System Usability Scale (SUS) dengan 10 pertanyaan. Hasil pengujian diisi oleh 31 responden dengan hasil SUS 70,24 dengan predikat Acceptable. Solusi Cari Kos PKU menyediakan filter lokasi dan harga untuk pencarian tepat sasaran. Informasi properti terverifikasi membantu pengguna membuat keputusan yang lebih baik dan cepat. Aplikasi ini diharapkan dapat menjadi referensi pengembangan platform pencarian hunian berbasis mobile yang lebih lengkap di masa mendatang. Penelitian ini juga menunjukkan bahwa pendekatan Design Thinking efektif diterapkan dalam perancangan UI/UX aplikasi berbasis kebutuhan pengguna, karena setiap tahapannya berfokus pada pemahaman mendalam terhadap permasalahan nyata yang dihadapi mahasiswa dan karyawan pencari kos. Dengan adanya fitur pencarian berbasis filter, sistem favorit, fitur pesan langsung ke pemilik properti, serta tampilan detail properti yang informatif, aplikasi Cari Kos PKU dirancang untuk memberikan pengalaman pengguna yang intuitif, efisien, dan menyenangkan. Hasil penelitian ini diharapkan dapat menjadi acuan bagi pengembang aplikasi sejenis dalam merancang platform pencarian hunian digital yang lebih baik khususnya untuk memenuhi kebutuhan mahasiswa dan karyawan di Kota Pekanbaru.
Spatial Data Analysis for Environmental and Climate Monitoring Using Google Earth Engine and Random Forest Classification Supiyandi Supiyandi; Ramlah binti Mailok
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.152

Abstract

Land-cover change is a primary driver of environmental degradation and local climate alteration, yet up-to-date, spatially explicit information remains scarce in rapidly developing regions such as North Sumatra, Indonesia. This study aims to develop an accurate, reproducible workflow for environmental and climate monitoring by integrating cloud-based spatial data processing with machine-learning classification. Multitemporal Sentinel-2 surface-reflectance imagery (2019 and 2024) and Landsat-derived land-surface temperature were processed on the Google Earth Engine (GEE) platform. Spectral bands were combined with vegetation, water, and built-up indices (NDVI, NDWI, NDBI, EVI, SAVI, BSI) and topographic data, after which a Random Forest (RF) classifier distinguished six land-cover classes from stratified training samples. The RF model achieved an overall accuracy of 92.4% and a kappa coefficient of 0.906, outperforming Classification and Regression Tree (86.1%) and Support Vector Machine (88.7%) baselines. NDVI, the near-infrared band, and NDWI were the most influential predictors. Between 2019 and 2024 the built-up area expanded by 18.7% while forest and cropland contracted, and these changes coincided with a measurable rise in land-surface temperature, confirming a strong inverse relationship between vegetation cover and surface heating. The results demonstrate that the GEE–RF approach provides a low-cost, scalable, and replicable basis for routine environmental and climate monitoring to support evidence-based regional planning.
Disaster-Responsive Governance dan Kompetensi Guru dalam Membangun Resiliensi Pendidikan pada Pendidikan Islam Pascabencana Banjir Alfian Sani
Prosiding Seminar Nasional Ilmu Komputer, Sosial Sains, Teknik dan Multi-Disiplin Ilmu Vol. 2 (2026)
Publisher : Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/ikosstemi.v2.153

Abstract

Floods are one of the most frequent threats to the continuity of the education system in Indonesia. Their impacts include not only damage to school infrastructure but also reduced quality of educational services, hampered learning processes, and weakened the resilience of educational institutions in facing crises. In the context of Islamic education, these challenges are increasingly complex because teachers are not only tasked with maintaining the continuity of learning but also carry out character development, psychosocial support, and strengthening students’ spiritual values. This study aims to analyze the relationship between Disaster-Responsive Governance and teacher competency in building educational resilience in Islamic educational units after flood disasters. The study used a qualitative approach with a case study design in flood-affected areas in Aceh Tamiang Regency. Data were collected through in-depth interviews, field observations, and analysis of policy documents and reports on educational disaster management. Data analysis was conducted using thematic analysis techniques through data reduction, categorization, interpretation, and conclusion drawing. The research findings indicate that low educational resilience is not solely due to the magnitude of the disaster’s impact, but is also influenced by weak disaster-responsive educational governance, limited coordination between stakeholders, and suboptimal teacher adaptive competencies in dealing with emergency situations. Teachers are required to play a broader role as facilitators of adaptive learning, psychosocial counselors, communication mediators with the community, and reinforcers of Islamic values ​​in the educational recovery process. This research offers a conceptual model that integrates Disaster-Responsive Governance, adaptive teacher competencies, and contextual factors as a foundation for building educational resilience in Islamic educational institutions. This model is expected to serve as the basis for developing more adaptive, inclusive, and sustainable educational policies in disaster-prone areas.

Page 1 of 1 | Total Record : 6

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 2 (2026) Vol. 1 (2025)