Claim Missing Document
Check
Articles

Found 33 Documents
Search

Comparative Analysis to Determine the Best Accuracy of Classification Methods Nengsih, Warnia; Fitrisia, Yuli; Fadhli, Mardhiah
ILKOM Jurnal Ilmiah Vol 14, No 2 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i2.1128.134-141

Abstract

The classification method is one of the methods of supervised learning and predictive learning. This method can be used to detect an object in the image presented, whether it is in accordance with the existing object in the training phase. There are several classification methods used, including Support Vector Machine (SVM), K-Nearest Neighbors (K-NN) and Decision Tree. To determine the accuracy in detecting these objects, it is necessary to measure the accuracy of each classification method used. The object that becomes simulation in this research is the object image of Guava and Pear fruit. Testing using confusion matrix. The results showed that the Support Vector Machine (SVM) method was able to detect with an accuracy of 98.09%. Then the K-Nearest Neighbors (K-NN) method with an accuracy of 98.06%, then the Decision Tree method with an accuracy of 97.57%. From the results of the accuracy test, it can be concluded that basically these three classification methods have good accuracy with a difference of 0.49% and the overall average accuracy of the classification of the three methods is 97.89%
Workshop Live Streaming Menggunakan OBS Untuk MGMP TIK Pekanbaru Ibnu Surya; Ivan Chatisa; Yoanda Alim Syahbana; Muhammad Ihsan Zul; Yuli Fitrisia; Jan Alif Kreshna; Harumin Harumin; Irgi Yoga Pangestu
Jurnal Pengabdian Kompetitif Vol. 5 No. 1 (2026): Jurnal Pengabdian Kompetitif (JPK)
Publisher : Komunitas Manajemen Kompetitif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35446/pengabdiankompetif.v5i1.2802

Abstract

OBS is open-source software that needs to be introduced to the community, particularly to organizations and companies with a high demand for live streaming communication. This needs to be introduced and optimized because the infrastructure is generally already available and running well and is almost evenly distributed among certain organizations, both companies and high schools. OBS can be applied for streaming communication purposes on Internet-based networks. This activity is a PkM, which is a collaboration between Polytechnic Caltex Riau and the Information and Communication Technology Subject Teacher Working Group (MGMP TIK) in Pekanbaru and Kampar, Riau. Live Streaming Workshop/training using OBS to introduce and deepen the material for ICT teachers to teach multimedia network material, streaming technology. For this purpose, training and evaluation were conducted before and after the workshop on teachers' knowledge of live streaming. Prior to the workshop, approximately 79% understood the material, After being introduced to the participants and trying out the practice, results showed that approximately 100% found it easy to understand and could be applied to support multimedia network practical work.
A Prototype-Driven Approach for e-Waste Redistribution Heni Rachmawati Santoso; Adriza Rafly Azlami; Yuli Fitrisia; Wenda Novayani
Jurnal Komputer Terapan Vol 12 No 1 (2026): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35143/jkt.v12i1.6906

Abstract

The rise of electronic waste (e-Waste) poses a serious environmental challenge due to the public's lack of awareness and limited access to standardized recycling facilities. This study proposes a community-based E-Waste redistribution model integrated with Circular Economy principles, implemented through a mobile platform. To ensure responsible E-Waste management, this architecture features a dedicated redistribution flow connecting end-users directly with verified recyclers. Furthermore, Location-Based Services (LBS) are implemented not merely for mapping, but as a spatial proximity-matching algorithm using the Haversine formula to optimize logistics. The system was developed using a prototyping methodology, encompassing comprehensive user requirement identification and two iterative design cycles based on qualitative user feedback. Functional evaluation via black-box testing validated a 100% success rate across all system integration scenarios. Moreover, usability testing involving 21 demographically targeted respondents, evaluated using a custom-developed questionnaire and yielded a feasibility score of 91.5%. These findings indicate a high level of user acceptability and interface effectiveness. Ultimately, this research contributes an algorithmic and architectural framework for communitydriven e-Waste management, establishing a viable digital solution for sustainable waste redistribution.