Multi-target detection of waste composition in complex environments based on an improved YOLOX-S model DOI
Rui Zhao,

Qihao Zeng,

Liping Zhan

et al.

Waste Management, Journal Year: 2024, Volume and Issue: 190, P. 398 - 408

Published: Oct. 14, 2024

Language: Английский

Efficient Differentiation of Biodegradable and Non-Biodegradable Municipal Waste Using a Novel MobileYOLO Algorithm DOI Creative Commons

S. Menaka,

Gayathri Arulanantham

Traitement du signal, Journal Year: 2023, Volume and Issue: 40(5), P. 1833 - 1842

Published: Oct. 30, 2023

In the realm of waste management, accurate identification biodegradable and nonbiodegradable items remains a critical challenge.An advanced real-time object detection method, termed "MobileYOLO", was proposed, leveraging strengths YOLO v4 framework.The MobileNetv2 network integrated, section conventional computation substituted with depth-wise separable convolutions utilizing PAnet head network.To enhance feature expressiveness capabilities during fusion, refined lightweight channel attention mechanism, known as Efficient Channel Attention (ECA), introduced.The Improved Single Stage Headless (ISSH) context module incorporated into micro-object branch to broaden receptive field.Evaluations conducted on KITTI dataset indicated an impressive accuracy 95.7%.Remarkably, when compared standard YOLOv4, MobileYOLO model exhibited reduction in parameters by 53.12M, decrease connectivity size one-fifth, augmentation speed 85%.

Language: Английский

Citations

3

An Automated Approach to Waste Classification Using Deep Learning DOI

S Loganayagi,

Usha Divakarla

Published: Feb. 22, 2023

Waste management has been done by humans through direct monitoring and classification of the products or items that are to be sorted-out. carried out in industries, hospitals, hotel tourism, food beverages, military other fields classify wastes as recyclable non-recyclable. In this research waste is implemented predict identify images into three classes organic, non-recyclable using a convolutional neural network model with inception-net layers. The study developed custom inception adding additional layers compares performance accuracy against basic Inceptionv3 model. used SGD (stochastic gradient descent) liner regression algorithm for categorical cross-entropy loss estimation. current uses ReLU function overcome under-fitting over-fitting issues. Dataset was taken from open-source data base. gained 77% whereas obtained 94% minimal value 3.

Language: Английский

Citations

2

Novel Deep Learning Approaches to Environmental Management with Sustainability DOI

Chunchu Suchith Kumar,

Chinnem Rama Mohan,

B. Santhosh Kumar

et al.

Published: May 9, 2024

Language: Английский

Citations

0

Towards Sustainable Waste Management: Exploring Machine Learning and Deep Learning Solutions for Biodegradable and Non-Biodegradable Waste Identification DOI

Rekha Subramani,

P. Kavitha,

S. Kamalakkannan

et al.

Published: May 3, 2024

Language: Английский

Citations

0

Multi-target detection of waste composition in complex environments based on an improved YOLOX-S model DOI
Rui Zhao,

Qihao Zeng,

Liping Zhan

et al.

Waste Management, Journal Year: 2024, Volume and Issue: 190, P. 398 - 408

Published: Oct. 14, 2024

Language: Английский

Citations

0