DBS-YOLO: A High-Precision Object Detection Algorithm for Hazardous Waste Images

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2024, Volume and Issue: 73, P. 1 - 15

Published: Jan. 1, 2024

Language: Английский

---

State of the Art and Potentialities of Graph-level Learning

ACM Computing Surveys, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 12, 2024

Graphs have a superior ability to represent relational data, like chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes set of graphs as input, has been applied many tasks including comparison, regression, classification, more. Traditional approaches learning heavily rely on hand-crafted features, such substructures. While these methods benefit from good interpretability, they often suffer computational bottlenecks cannot skirt the graph isomorphism problem. Conversely, deep helped adapt growing scale by extracting features automatically encoding into low-dimensional representations. As result, responsible for successes. Yet, no comprehensive survey reviews starting with traditional moving through approaches. This article fills this gap frames representative algorithms systematic taxonomy covering neural networks, pooling. In addition, evolution interaction between four branches within their developments are examined provide an in-depth analysis. is followed brief review benchmark datasets, evaluation metrics, common downstream applications. Finally, concludes discussion 12 current future directions in booming field.

Language: Английский

---

Multimodal Dual Cross-Attention Fusion Strategy for Autonomous Garbage Classification System

IEEE Transactions on Industrial Informatics, Journal Year: 2024, Volume and Issue: 20(11), P. 13319 - 13329

Published: Aug. 9, 2024

Language: Английский

---

Machine vision-based detection of forbidden elements in the high-speed automatic scrap sorting line

Waste Management, Journal Year: 2024, Volume and Issue: 189, P. 243 - 253

Published: Aug. 30, 2024

Highly efficient industrial sorting lines require fast and reliable classification methods. Various types of sensors are used to measure the features an object determine which output class it belongs to. One technique involves use RGB camera a machine learning classifier. The paper is focused on protecting process against prohibited dangerous items potentially present in sorted material that pose threat or subsequent metallurgical process. To achieve this, convolutional neural network classifier was applied under real-life conditions detect forbidden elements copper-based metal scrap. A laboratory stand simulating working high-speed scrap line prepared. Using this custom stand, training test sets for were gathered labeled. An image preprocessing algorithm designed increase robustness resulting element detector system. performance multiple architectures data set augmentations analyzed. highest accuracy 98.03% F1-score 97.16% achieved with DenseNet-based results show feasibility using presented solution line.

Language: Английский

---

Lightweight deep learning model for underwater waste segmentation based on sonar images

Waste Management, Journal Year: 2024, Volume and Issue: 190, P. 63 - 73

Published: Sept. 14, 2024

Language: Английский

---

Intelligent electronic components waste detection in complex occlusion environments based on the Focusing Dynamic Channel-You Only Look Once model

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: unknown, P. 144425 - 144425

Published: Dec. 1, 2024

Language: Английский

---

Topic-sentiment analysis of citizen environmental complaints in China: Using a Stacking-BERT model

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 371, P. 123112 - 123112

Published: Oct. 31, 2024

Language: Английский

---

Wimplebin: an AI-based recycle bin for a better waste management

Journal of Material Cycles and Waste Management, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 17, 2024

Language: Английский

---