Claim Missing Document
Check
Articles

Found 2 Documents
Search

Blanket Pixel-Based Segmentation for Detecting Object Geometry Sucipto, Putra Wisnu Agung; Wibowo, Danang Arengga; Firasanti , Annisa; Bakri , Muhammad Amin; Yaqin , Khusnul
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 13 No. 1 (2025): Maret 2025
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v13i1.10727

Abstract

This study aims to develop a blanket pixel-based approach to construct object geometry for image segmentation. Object geometry can be formed from a collection of pixels generated from the edge detection process. However, edge pixels that will be included in a segment must go through an identification process to determine their identity, with a reference segment as a reference for labeling. This work proposes the terminology of blanket pixels, namely pixels that surround a pixel that does not yet have an identity due to being isolated from the surrounding segments, as a spatial exoskeleton for the labeling process. This approach has been tested, and the results show that we successfully detect the structure of tilapia egg circles with clear fortifications when the scanning radius parameter is set to 10 pixels and the proximity between the surrounding pixels and the labeled pixels is 11.8 pixels. Out of 114 egg circles, this method successfully detected 105 eggs, with 9 small eggs (2–3 pixels in diameter) undetected, resulting in a detection ratio of 92.11%. The blanket pixel approach effectively recognizes and reclassifies isolated pixel labels. This approach supports the process of labeling pixels in areas with significant ambiguity.
SMART WEIGHING FOR WASTE MANAGEMENT SYSTEM USING INTEGRATION INTERNET OF THINGS AND ARTIFICIAL INTELLIGENCE TO ASSIST CIRCULAR ECONOMICS Sendari, Siti; Mokthar, Norrima binti; Ramadan, Bimastyaji Surya; Ramadani, Bakhrul Mukhid Fadilah; Pramesti, Fadila Claudia; A'ini, Qurrotul; Wibowo, Danang Arengga; Sucipto, Putra Wisnu Agung; Rahmawati, Yuni; Wibowo, Fauzy Satrio
INDONESIAN JOURNAL OF URBAN AND ENVIRONMENTAL TECHNOLOGY VOLUME 8, NUMBER 2, OCTOBER 2025
Publisher : Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/urbanenvirotech.v8i2.23959

Abstract

Aims: This study was aimed to Supit Urang Landfill in Malang, East Java, Indonesia, urgently needs a smart waste management system because it is strategically important as a large landfill with a monthly operating capacity of 4.560 trucks. Landfill management is very challenging due to some cases, such as overcapacity, inefficient waste sorting, and environmental risks. Methodology and results: The research introduced an integration of Internet of Things (IoT) and Artificial Intelligence (AI) into the waste management system to support the principles of a circular economy. IoT was applied for real time monitoring of waste conditions, while AI was utilized for big data analytics, enabling predictions, decision-making support, and policy recommendations. The results demonstrated that the proposed system improves efficiency and cost-effectiveness by reducing the amount of waste disposed of in the landfill and optimizing the waste sorting and recycling process. Conclusion, significance and impact study: The study concludes that the transformation toward a sustainable waste management model is urgently needed and can be achieved through AIoT integration. This innovation supports circular economy practices by enhancing waste reduction, reuse, and recycling. The successful implementation at Supit Urang could serve as a scalable model for other landfills across Indonesia, thereby contributing to national strategies for sustainable waste management. This technological intervention not only improves environmental outcomes by reducing pollution and conserving resources but also fosters economic development through efficient resource utilization and job creation in the recycling and waste processing sectors.