Explore the vast range of titles available.

Due to the sharp increase in household waste, its separate collection is essential in order to reduce the huge amount of household waste, since it is difficult to recycle trash without separate collection. However, since it is costly and time-consuming to separate trash manually, it is crucial to develop an automatic system for separate collection using deep learning and computer vision. In this paper, we propose two Anchor-free-based Recyclable Trash Detection Networks (ARTD-Net) which can recognize overlapped multiple wastes of different types efficiently by using edgeless modules: ARTD-Net1 and ARTD-Net2. The former is an anchor-free based one-stage deep learning model which consists of three modules: centralized feature extraction, multiscale feature extraction and prediction. The centralized feature extraction module in backbone architecture focuses on extracting features around the center of the input image to improve detection accuracy. The multiscale feature extraction module provides feature maps of different scales through bottom-up and top-down pathways. The prediction module improves classification accuracy of multiple objects based on edge weights adjustments for each instance. The latter is an anchor-free based multi-stage deep learning model which can efficiently finds each of waste regions by additionally exploiting region proposal network and RoIAlign. It sequentially performs classification and regression to improve accuracy. Therefore, ARTD-Net2 is more accurate than ARTD-Net1, while ARTD-Net1 is faster than ARTD-Net2. We shall show that our proposed ARTD-Net1 and ARTD-Net2 methods achieve competitive performance in mean average precision and F1 score compared to other deep learning models. The existing datasets have several problems that do not deal with the important class of wastes produced commonly in the real world, and they also do not consider the complex arrangement of multiple wastes with different types. Moreover, most of the existing datasets have an insufficient number of images with low resolution. We shall present a new recyclables dataset which is composed of a large number of high-resolution waste images with additional essential classes. We shall show that waste detection performance is improved by providing various images with the complex arrangement of overlapped multiple wastes with different types.

This research aims to show the positive and negative indirect effects of COVID-19 on municipal solid waste management systems, especially for plastic waste and food waste. The COVID-19 pandemic has affected the entire waste management sector. As the pandemic spread and lockdowns were enforced in many countries, government and municipal waste operators had to quickly adapt their waste management programs and procedures to the situation. In the pandemic condition, waste generation has switched from industry and commercial to domestic areas. Reduced recycling activities have made municipal waste collection and disposal more difficult. This paper focuses on all the challenges and it’s possible resolutions for managing food and plastic waste during the pandemic of COVID-19.

Over the past 30 years, the Kingdom of Saudi Arabia (KSA) has recorded rapid economic growth and development rates matched by corresponding levels of consumption. This has led to an exponential increase in the volume of municipal solid waste. Even if the bulk share of this waste is recyclable, the propensity of households to engage in the recycling of waste has so far produced a negligible effect. Arguably, in the context of the pervasive digitalization of public and private spaces, accompanied by the developments in information and communication technology (ICT), best conceptualized by reference to the concepts of smart cities and circular economy, it is natural to expect ICT and policy objectives to converge in order to encourage and enable greater engagement with waste segregation and recycling amongst households. Against this backdrop, this paper explores the feasibility and ways of increasing households’ participation in recyclable waste collection, segregation, and disposal in a context devoid of a top-down city-level waste management policy. To this end, the design thinking approach was employed to identify factors inhibiting/facilitating households’ engaging in recycling. A variety of ideation techniques were adopted in subsequent stages of the design thinking process, including interviews with stakeholders from the government and industry sectors, surveys with Jeddah households (N = 446), an eight week-long recyclable waste collection experiment, and feedback surveys (N = 46). The results suggest that applying relatively simple and resource-savvy tools aimed at promoting household recyclable waste collection has substantial potential. This, in turn, not only feeds into the debate on smart cities but also into the research of public policy.

Solid waste management (SWM) is one of the most neglected aspects and becoming a challenge for India as well as other developing nations' environment. India is one of the world's large and fastest-growing economy. Based on the trends in different nations like the US, China and European countries, it is clear that a developing economy of the nation and population of the country is also playing a vital role in the increasing rate of solid waste generation. Unsegregated waste is the root cause of the inefficient municipal solid waste management (MSWM) systems in India. The existing approach to managing the MSW such as collection, transportation and treatment results in poor utilization of resources. This review paper addresses the current status of MSWM in India. In this paper, various issues and challenges to obtain 100 % source segregated municipal solid waste are also discussed through different cases of urban areas. A way forward through an overview of the municipal waste management policies and practices adopted is being presented in the paper.

This quasi-experimental study evaluated the effects of waste segregation training on medical and recyclable waste generation in the operating theater of Ankara University Cebeci Hospital. Conducted between March and June 2024, the study included pre-training, post-training, and two-month follow-up waste measurements, alongside a survey assessing staff awareness. A total of 53 operating room staff participated. Training significantly increased the amount of recyclable waste per surgery (from 1.30 kg to 1.80 kg, p  = 0.01) in the first month post-training. Although medical waste per surgery decreased (from 4.92 kg to 4.14 kg), the reduction was not statistically significant ( p  = 0.09). However, two months later, waste levels began reverting to baseline (recyclable: 1.79 kg; medical: 5.07 kg per surgery), suggesting the effect of a single training session may diminish over time. Notably, 40% of doctors lacked sufficient knowledge pre-training, and those favoring training were often the least informed ( p  = 0.02), highlighting gaps in prior education. This study emphasizes the need for repeated and tailored training programs to reinforce sustainable waste practices in surgical environments.

Recyclable waste sorting has become a key step for promoting the development of a circular economy with the gradual realization of carbon neutrality around the world. This study aims to develop an intelligent and efficient method for recyclable waste sorting by the method of deep learning. Thus, RWNet models, which refers to various ResNet structures (ResNet-18, ResNet-34, ResNet-50, ResNet-101, and ResNet-152) based on transfer learning, were proposed to classify different types of recyclable waste. Cyclical learning rate and data augmentation were taken to improve the performance of RWNet models. In addition, accuracy, precision, recall, F1 score, and ROC were taken to evaluate the performance of RWNet models. Results showed that the accuracy of various RWNet models is almost at 88%, and the best accuracy is 88.8% in RWNet-152. The highest precision, recall, and F1 score in terms of weighted average value appeared in RWNet-101 (89.9%), RWNet-152 (88.8%), and RWNet-152 (88.9%), respectively. The area under the ROC curve (AUC) is higher than 0.9, except for the AUC value of plastic (0.85), which indicated that most of the recyclable waste can be well sorted by RWNet models. This study demonstrates the good performance of RWNet models that can be used to automatically sort most of the recyclable waste, which paves the way for better recyclable waste management.

The goal of this paper is to conduct an environmental analysis of a municipal solid waste management system in a midsized region of Southeast Brazil with two million inhabitants. While the current municipal solid waste management system has already eradicated dumps, it landfills practically all its waste, with < 2% open composting and recycling. Therefore, alternatives such as closed composting (CC), anaerobic digestion (AD) with electricity or biomethane production, and incineration are proposed via scenarios in which legal requirements are observed and diversion targets are set. Life cycle assessment (LCA) was performed using EASETECH, a specific software for municipal solid waste (MSW) management systems. The results show that the high diversions scenario (70% recyclables/biowaste) with upgraded biomethane from AD and recycling had 76% greater environmental savings than the similar scenario with the new Brazilian diversion targets (25.8% recyclables, 18.1% biowaste). CC performed much worse than AD, with 80% less savings, although it was marginally better than open composting, with a 95% difference in savings. Despite the benefits of incineration, these scenarios were penalized for their toxicity. Recycling is always recommended if feasible.

Low-value recyclable waste (LVRW) is an essential component of municipal domestic waste. Due to the lightweight and high quantity characteristics, the main disposal methods of LVRW are incineration and landfill, which are not conducive to the environmental protection requirements and the goal of carbon neutrality and emission peak. The paper focuses on the delicate separation of LVRW to realize a cost-effective solution for waste sorting. Firstly, a machine vision (MV) pneumatic sorting equipment was designed based on the MV detection system. Then, a large number of authentic waste images were captured and labeled to train a high accuracy LVRW prediction model through semi-automatic labeling and transfer learning. Subsequently, the LVRW waste sorting solution was designed and constructed, and a comparative experimental study about the MV sorting method and the whole solution was conducted. The experimental results show that the MV sorting method achieves 92% sorting accuracy, and the solution can dispose of 65 tons of LVRW per day with a waste recycling rate of 37.7%. The sorting equipment and solutions developed in the paper can effectively improve the resource utilization of LVRW at a lower cost.

Low-value recyclable waste accounts for a large portion of urban waste output in many modern cities. The improper management and disposal of LVRW result in environmental pollution and a waste of resources. Given the characteristics of a high recovery cost and low recovery income of low-value recyclables, it is difficult to obtain a satisfactory waste disposal effect by completely relying on the market mechanism. It is thus necessary for the government to implement effective subsidies for multiple subjects in the urban waste recycling system (UWRS). This study examines the independent roles of four subsidy policies—subsidy to the third-party waste disposal institutions, subsidy to a state-owned waste disposal institution, R&D subsidy for green technology, and subsidy for government publicity—and develops a system dynamics model to verify the performance of the UWRS under different combinations of subsidy-based policies under multiple scenarios. Data on urban waste disposal for Guangzhou from 2019 and 2020 were used to validate and simulate the model. A sensitivity analysis of the main exogenous variables was carried out, and the conclusions are as follows: (1) On the premise of a fixed subsidy capital pool, a mixed subsidy policy produced the best impact on the UWRS. (2) The total subsidy needed to reach a certain threshold; otherwise, the mixed subsidy policy did not improve the UWRS. The total subsidy produced diminishing returns once it had exceeded the threshold. (3) Appropriately reducing subsidies for the third-party waste disposal institutions within a reasonable range does not affect the performance of the UWRS. (4) The effect of government publicity has short-term advantages, while the long-term potential of green technology is greater. Multi-agent coordination and the guidance of the market mechanism are important priorities in the design of subsidy-based policies. In addition, the trade-off between subjects needs attention, and a plan for mixed subsidy policies needs to be designed and implemented according to the response periods of different policies. The research here provides theoretical support for the government for designing subsidy-based policies.

The estimated increase in urban solid waste generation in the near future worldwide may negatively impact the environment and public health, and produce a significant economic impact on solid waste management. Recycling is crucial in mitigating this solid waste generation growth by diverting materials from landfills, reducing greenhouse gas emissions and pollution, conserving resources, and extending end-of-life strategies. In this study, we address the bin location–allocation problem for the collection of recyclable household waste, a key challenge in the context of the circular economy and efforts to mitigate the sustained growth of household waste generation. To tackle this problem, this study generalizes a previous mixed-integer linear programming (MILP) model to address different types of waste, particularly recyclable household waste, while minimizing total bin costs and ensuring that each generation point is assigned to the nearest collection site within a given threshold travel distance. Additionally, the model compares single and multi-stream collection strategies. For each case, we evaluate the options of locating recycling bins at road intersections and in open public spaces. Real-world data from the commune of Quinta Normal in Santiago, Chile is used to test our approach. This study also reports results of a sensitivity analysis of key parameters, including the generated household recyclable waste and the maximum distances users are willing to travel to dispose of their recyclable waste. Finally, managerial implications that emerge from this study are discussed, which may help authorities improve recyclable household waste collection, and outline future research directions.