Publisher

POLITANI SAMARINDAPOLITANI SAMARINDA

Journal TEPIANTEPIAN Abstract

As the global waste crisis grows, businesses are under pressure to improve waste management. AI, especially image recognition, offers innovative solutions for optimizing waste sorting. By using Convolutional Neural Networks (CNNs) and deep learning models trained on extensive datasets of waste images, companies can automate the classification of materials such as plastic, glass, and metal with high accuracy. This reduces reliance on manual labor, minimizes human error, and improves the speed and precision of sorting. Cameras capture images of waste items on conveyor belts, which are then analyzed by AI algorithms in real time. These systems continuously improve through feedback loops and reinforcement learning, leading to more efficient sorting over time. The result is higher recycling rates, reduced operational costs, and enhanced sustainability outcomes. AI-based systems enable businesses to decrease waste sent to landfills, recover valuable materials, and lower costs associated with waste management. With continuous updates to their training data and the use of edge computing for real-time processing, these solutions represent a major advancement in sustainable business practices.

Conclusion

AI-driven waste sorting is a powerful tool that offers businesses a path to more efficient and sustainable waste management practices.By integrating machine learning and image recognition, companies can significantly improve their waste management operations, reducing environmental impacts and driving cost savings.

Future Research

Berdasarkan penelitian ini, terdapat beberapa saran penelitian lanjutan yang dapat dilakukan untuk lebih mengembangkan penerapan AI dalam pengelolaan sampah bisnis. Pertama, penelitian dapat difokuskan pada pengembangan algoritma AI yang lebih adaptif terhadap variasi jenis sampah yang semakin kompleks, termasuk sampah dengan kemasan yang inovatif dan sulit diidentifikasi. Hal ini dapat dilakukan dengan memperluas dataset pelatihan dan menggunakan teknik pembelajaran transfer untuk meningkatkan kemampuan generalisasi model. Kedua, penelitian dapat mengeksplorasi integrasi sensor-sensor tambahan, seperti sensor berat dan komposisi material, untuk memberikan informasi yang lebih lengkap kepada sistem AI, sehingga meningkatkan akurasi klasifikasi dan pemilahan sampah. Ketiga, penelitian dapat mengkaji penerapan teknologi edge computing yang lebih canggih untuk memungkinkan pemrosesan data secara real-time di lokasi pengolahan sampah, sehingga mengurangi latensi dan meningkatkan efisiensi operasional. Dengan menggabungkan ketiga saran ini, diharapkan dapat tercipta sistem pengelolaan sampah bisnis yang lebih cerdas, efisien, dan berkelanjutan, serta berkontribusi pada upaya pelestarian lingkungan.

References

1. AI for Enhanced Efficiency in Business Waste Sorting Strategies | TEPIAN. ai enhanced efficiency business... doi.org/10.51967/tepian.v6i3.3379AI for Enhanced Efficiency in Business Waste Sorting Strategies TEPIAN ai enhanced efficiency business doi 10 51967 tepian v6i3 3379
2. Applications of artificial intelligence in urban solid waste management: A systematic literature review... ijirss.com/index.php/ijirss/article/view/6010Applications of artificial intelligence in urban solid waste management A systematic literature review ijirss index php ijirss article view 6010

Subjects

1. #machine learning#machine learning
2. #deep learning#deep learning

Metadata

File size	839.61 KB
Pages	8
Short Link	https://juris.id/p-3cY
Lookup Links	Google ScholarGoogle Scholar, Semantic ScholarSemantic Scholar, CORE.ac.ukCORE.ac.uk, WorldcatWorldcat, ZenodoZenodo, Research GateResearch Gate, Academia.eduAcademia.edu, OpenAlexOpenAlex, Hollis HarvardHollis Harvard
DMCA	Report