MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting

Lin, Kunsen; Zhao, Youcai; Wang, Lina; Shi, Wenjie; Cui, Feifei; Zhou, Tao

doi:10.1007/s11783-023-1677-1

Cited by 15 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We tried to test the algorithms that were resulted to be good by other researchers. We considered mobilenet [10] that got accuracy of 93.35% (15% test size) using a quite similar Kaggle dataset of size around 2400 images. For our research we evaluated mobilenet model using Kaggle dataset of size 2527.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…Lin, K., Zhao, Y., Wang, L. et al (2023) did a study on A visual deep machine learning method adopting transfer learning based upon ResNet50 for municipal solid waste sorting. Deep machine learning can help MSW sorting becoming into a smarter and more e cient mode The accuracy of ResNet50 on the MSW testing dataset was 88.50% and then improved, suggesting that ResNet50 model performs well in MSWclassi cation[10]…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study of ML Algorithms for Garbage Classification

Buchade,

Bhoite

2024

Preprint

View full text Add to dashboard Cite

In today's world, the escalating waste crisis demands effective garbage classification strategies. As population growth and evolving needs contribute to unprecedented waste generation, repurposing items through recycling, reproduction, or reuse becomes imperative. Proper garbage classification is pivotal in realizing these goals. This paper presents a concise yet comprehensive comparative study of machine learning algorithms for garbage classification. The primary objectives include comparing the performance of MobileNetV2, InceptionV3, and ResNet in garbage classification and scrutinizing optimal algorithms employed by researchers. The dataset comprises six garbage classes: cardboard, metal, paper, plastic, glass, and trash. Through rigorous evaluation, insights into algorithmic performance are presented. MobileNetV2 stands out, achieving a remarkable 94.48% accuracy on the validation set with minimal loss. InceptionV3 and ResNet50 yield accuracies of 86.08% and 88.54%, respectively. This study not only contributes to garbage classification knowledge but also highlights the real-world potential of the top-performing algorithm. As we address waste management complexities, this research signifies a step toward implementing efficient and accurate garbage classification systems for a sustainable future.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Comparative Study of ML Algorithms for Garbage Classification

Buchade,

Bhoite

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, DL technologies have already been successfully applied in the sorting for MSW, − ,,,− or in a more specific area such as the classification of e-wastes, , C&D wastes, , food trays, or recyclable waste. ,,− The classification accuracies varied in different studies due to the specific classification tasks. Generally, the best classification accuracies reported from recent studies ranged from 90.00% to 99.60% for single-label waste sorting with consistent background, ,,,,, 82.80% to 96.96% for single-label waste sorting with inconsistent backgrounds, ,,− and 73.00% to 95.20% for multilabel waste sorting, ,,,,,,,, which are significantly better compared with manual sorting .…”

Section: Where and How Data Science Has Helped The Circular Economy?mentioning

confidence: 99%

Section: Where and How Data Science Has Helped The Circular Economy?mentioning

confidence: 99%

Data Science Applications in Circular Economy: Trends, Status, and Future

Zhao,

Yu,

Wang

et al. 2024

Environ. Sci. Technol.

View full text Add to dashboard Cite

The circular economy (CE) aims to decouple the growth of the economy from the consumption of finite resources through strategies, such as eliminating waste, circulating materials in use, and regenerating natural systems. Due to the rapid development of data science (DS), promising progress has been made in the transition toward CE in the past decade. DS offers various methods to achieve accurate predictions, accelerate product sustainable design, prolong asset life, optimize the infrastructure needed to circulate materials, and provide evidence-based insights. Despite the exciting scientific advances in this field, there still lacks a comprehensive review on this topic to summarize past achievements, synthesize knowledge gained, and navigate future research directions. In this paper, we try to summarize how DS accelerated the transition to CE. We conducted a critical review of where and how DS has helped the CE transition with a focus on four areas including (1) characterizing socioeconomic metabolism, (2) reducing unnecessary waste generation by enhancing material efficiency and optimizing product design, (3) extending product lifetime through repair, and (4) facilitating waste reuse and recycling. We also introduced the limitations and challenges in the current applications and discussed opportunities to provide a clear roadmap for future research in this field.

show abstract

“…Recently, a powerful tool named transfer learning has been used to solve the distribution discrepancy of intelligent fault diagnosis areas [ 37 ]. The difference between classical intelligent fault diagnosis and transfer learning is that the latter has two datasets, source domain and target domain.…”

Section: Introductionmentioning

confidence: 99%

A Domain Adaption ResNet Model to Detect Faults in Roller Bearings Using Vibro-Acoustic Data

Liu

Xiang

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

Intelligent fault diagnosis of roller bearings is facing two important problems, one is that train and test datasets have the same distribution, and the other is the installation positions of accelerometer sensors are limited in industrial environments, and the collected signals are often polluted by background noise. In the recent years, the discrepancy between train and test datasets is decreased by introducing the idea of transfer learning to solve the first issue. In addition, the non-contact sensors will replace the contact sensors. In this paper, a domain adaption residual neural network (DA-ResNet) model using maximum mean discrepancy (MMD) and a residual connection is constructed for cross-domain diagnosis of roller bearings based on acoustic and vibration data. MMD is used to minimize the distribution discrepancy between the source and target domains, thereby improving the transferability of the learned features. Acoustic and vibration signals from three directions are simultaneously sampled to provide more complete bearing information. Two experimental cases are conducted to test the ideas presented. The first is to verify the necessity of multi-source data, and the second is to demonstrate that transfer operation can improve recognition accuracy in fault diagnosis.

show abstract

MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting

Abstract: MSWNet was proposed to classify municipal solid waste.• Transfer learning could promote the performance of MSWNet. • Cyclical learning rate was adopted to quickly tune hyperparameters.

Cited by 15 publications

References 37 publications

Comparative Study of ML Algorithms for Garbage Classification

Comparative Study of ML Algorithms for Garbage Classification

Data Science Applications in Circular Economy: Trends, Status, and Future

A Domain Adaption ResNet Model to Detect Faults in Roller Bearings Using Vibro-Acoustic Data

Contact Info

Product

Resources

About