Waste Sorting Research Articles

Deep Learning Architectures for Waste Detection: A Systematic Literature Review

Increasing population growth contributes to the increasing amount of waste generated, creating problems in its management. One possible alternative is the usage of deep learning-based artificial intelligence technology, which can be applied for automated waste identification and classification. This research follows Systematic Literature Review (SLR) with the aim of evaluating the performance of various deep learning architectures in waste detection. Out of 547 articles identified, 20 were synthesized with the use of selective criteria. The synthesis of the evidence shows that architectures like YOLO, Faster R-CNN, and EfficientNet have been proven to be effective in the various datasets for waste detection. Furthermore, certain other models, such as ResNet-50B and DenseNet121, performed very well in image classification with accuracy values above 90%. In this research, several challenges were identified, including high computing power and computational magnitude. For future work, the optimization of models as well as the use of standard datasets such as TrashNet and TACO are recommended research directions that might help in developing an effective, efficient, and sustainable waste sorting system.

Honeybee Bioaccumulation as a Tool for Assessing the Environmental Quality of an Area Affected by the Activity of a Municipal Waste Sorting Facility (Central Italy)

The management of municipal solid waste presents a significant challenge for cities. Facilities dedicated to sorting, treating, and recycling waste (including plastic, glass, metals, aluminium, and wood) play a crucial environmental role in urban areas, contributing to sustainable development. Since combustion processes are not involved, any potential chemical impact of the facility on the surrounding area are likely to result from the emissions of metals and metalloids. In this study, the bioaccumulation of Al, As, Cd, Co, Cr, Cu, Fe, Hg, Mn, Ni, Pb, V, and Zn in the tissues of honeybees (Apis mellifera ligustica) was employed as a reference to assess the environmental quality of the area near a municipal waste sorting and storage facility located in Ponte Rio, Perugia (Umbria, Central Italy), which serves as the case study here. No higher contamination levels were found in the facility area compared to the suburban territory of Perugia, where the bioaccumulation levels of these elements in honeybees frequently exhibited higher values. The application of the Honeybee Contamination Index (HCI) confirmed these results. Therefore, the operation of this waste sorting facility is sustainable concerning environmental contamination by chemicals.

Artificial Intelligence in Waste Sorting: Advancing Recycling Processes in Greece Through Ai-Driven Solutions

The integration of Artificial Intelligence (AI) in waste sorting presents a transformative opportunity to enhance recycling processes, addressing inefficiencies and environmental challenges. This study investigates the application of AI-driven technologies within Greece, focusing on improving material classification, reducing contamination, and optimizing waste management practices. By leveraging advanced image recognition, machine learning algorithms, and robotic systems, the research demonstrates AI's potential to overcome infrastructure deficiencies and high operational costs, while fostering sustainability. A comprehensive analysis identifies socio-economic and environmental benefits, evaluates current barriers, and proposes a scalable framework for AI implementation. The findings aim to guide policymakers, industry stakeholders, and environmental organizations in adopting AI as a pivotal tool for advancing waste management and achieving global sustainability targets.

Integrated Waste Management in the Circular Economy Era: Insights from Research and Practice

This Special Issue on integrated waste management explores innovative approaches and multifaceted strategies aimed at addressing the critical challenges facing modern waste management systems. The featured eight original research articles cover diverse topics, including sewage sludge valorization, municipal waste biodrying, recyclables collection optimization, biomass-to-energy policies, and the management of compostable packaging waste. Technological advancements, such as AI-driven waste sorting and route optimization algorithms, are highlighted alongside policy frameworks supporting circular economy principles. The studies also address barriers to implementation, including public awareness gaps, technological disparities, and financial constraints, while emphasizing the importance of stakeholder collaboration across governments, industries, and communities. Additionally, environmental risks associated with waste management practices, such as nanoparticle contamination and leachate emissions from ashes, are critically analyzed. This Special Issue provides a holistic perspective on waste management, combining technical innovations, environmental stewardship, and policy integration. The insights of the works published in this Special Issue aim to guide researchers, policy-makers, and practitioners toward building resilient, sustainable, and resource-efficient waste management systems in alignment with global sustainability goals.

PLC-Controlled Intelligent Conveyor System with AI-Enhanced Vision for Efficient Waste Sorting

Current waste sorting mechanisms, particularly those relying on manual processes, semi-automated systems, or technologies without Artificial Intelligence (AI) integration, are hindered by inefficiencies, inaccuracies, and limited scalability, reducing their effectiveness in meeting growing waste management demands. This study introduces a prototype waste sorting machine that integrates an AI-driven vision system with a Programmable Logic Controller (PLC) for high-accuracy automated waste sorting. The system, powered by the YOLOv8 deep learning model, achieved sorting accuracies of 88% for metal cans, 75% for paper, and 91% for plastic bottles, with an overall precision of 90%, a recall of 80%, and a mean average precision (mAP50) of 86%. The vision system provides real-time classification, while the PLC manages conveyor and actuator operations to ensure seamless sorting. Experimental results in a controlled environment validate the system’s high accuracy, minimal processing delays, and scalability for industrial recycling applications. This innovative integration of AI vision with PLC automation enhances sorting efficiency, reduces ecological impacts, and minimizes labor dependency. Furthermore, the system aligns with sustainable waste management practices, promoting circular economy principles and advancing the Sustainable Development Goals (SDGs).

Comparative analysis of three methods for estimating the compositions of construction waste.

Determination of the relative compositions of the mixed construction waste is crucial and an important step to enhance resource management. This information influences the design of construction waste recycling and sorting facilities, and aids in formulating effective management strategies for recycled and sorted waste products. However, different methods for waste sorting and composition recognition possess distinct characteristics and only apply to specific practical scenarios. In this study, three methods are compared: (i) manual sorting as a reference method, (ii) a manual image recognition method using infrared thermal imaging, and (iii) a deep learning-based image recognition method based on the SegFormer semantic segmentation model. The comparison focuses on accuracy, preferences, prerequisites, socio-environmental impacts, costs, and improvement potential. Results show that both manual and deep learning-based image recognition methods yield comparable accuracy to manual sorting for inert waste, with relative errors below 5.2%, but relatively higher recognition errors for non-inert waste. Overall, manual sorting remains the most cost-effective and fastest method, despite its high labor demand, spatial constraints, environmental impacts, and limited improvement potential. In comparison, manual image recognition requires approximately 9.2 times the processing time and 2.3 times the cost of manual sorting, while deep learning-based image recognition incurs about 9.9 times the time and 2.5 times the cost. Nevertheless, both image recognition methods offer potential environmental benefits and long-term efficiency gains.

Machine learning-based automated waste sorting in the construction industry: A comparative competitiveness case study.

This article presents a comparative analysis of the circularity and cost-efficiency of two distinct construction material recycling processes: ML-based automated sorting (MLAS) and conventional sorting technologies. Empirical data was collected from two Finnish companies, providing a robust foundation for this comparison. Our study examines the operational specifics, economic implications, and environmental impacts of each method, highlighting the advantages and drawbacks. By leveraging data-driven insights, we aim to illustrate how MLAS can enhance recycling efficiency and sustainability compared to traditional methods. In our cost modeling over a seven-year period, MLAS achieved a cumulative cost of €12.76 million, significantly lower than CS, which incurred €21.47 million, underscoring the long-term cost efficiency of MLAS. The findings underscore the potential for advanced AI technologies to revolutionize waste management practices, offering significant improvements in sorting accuracy, material recovery rates, and overall cost-effectiveness. This analysis provides valuable perspectives for stakeholders in the construction and waste management industries, emphasizing the importance of integrating innovative technologies to achieve higher circularity and sustainability goals.

AI-based plastic waste sorting method utilizing object detection models for enhanced classification.

The export ban on plastic waste by China has brought domestic plastic recycling to the forefront of environmental concerns, with sorting being a crucial step in the recycling process. This study assessed the performance of advanced AI models, Mask R-CNN, and YOLO v8, in enhancing plastic waste sorting. The models were evaluated in terms of accuracy, mean average precision (mAP), precision, recall, F1 score, and inference time, with hyperparameter tuning performed through grid search. Mask R-CNN, with an accuracy of 0.912 and mAP of 0.911, outperformed YOLO v8 in tasks requiring detailed segmentation, despite a longer inference time of 200-350ms. Conversely, YOLO v8, with an accuracy of 0.867 and mAP of 0.922, excelled in real-time applications owing to its shorter inference time of 80-160ms. This study underscores the importance of selecting the appropriate model based on specific application requirements.

Sosialisasi Pembuatan Pupuk Organik dari Limbah Organik Rumah Tangga Berbantu Compost Bag

Household waste has become a pressing issue that needs to be addressed immediately, starting from the household level. Integrated solutions for household waste management have been implemented, both in the form of local regulations and direct socialization of household waste management to residents. However, optimization has not yet been achieved due to the increasing amount of household waste each year. One of the contributions from universities is to provide socialization and training on household waste management, covering materials on the sorting of organic and inorganic waste, the making of organic fertilizer for the community, the dissemination of organic fertilizer use, and an explanation of the impacts of poorly managed waste from an environmental perspective. The program implemented in this community service is the socialization of organic fertilizer making assisted by compost bags in Kedanyang Village, Gresik. Organic fertilizer made using compost bags is rich in carbon and nitrogen compounds, which are good for plant growth. This socialization also aims to reduce the impact of waste disposal on the environment, such as soil, water, and air pollution, and its effects on human health. In this compost bag method, the basic materials are dry and wet waste in a certain ratio, assisted by EM4 activator so that the composting process can run better. Organic fertilizer is made within 3-4 weeks before use and is in solid form.

Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques

The expansion of LEAN and small batch manufacturing demands flexible automated workstations capable of switching between sorting various wastes over time. To address this challenge, our study is focused on assessing the ability of the Segment Anything Model (SAM) family of deep learning architectures to separate highly variable objects during robotic waste sorting. The proposed two-step procedure for generic versatile visual waste sorting is based on the SAM architectures (original SAM, FastSAM, MobileSAMv2, and EfficientSAM) for waste object extraction from raw images, and the use of classification architecture (MobileNetV2, VGG19, Dense-Net, Squeeze-Net, ResNet, and Inception-v3) for accurate waste sorting. Such a pipeline brings two key advantages that make it more applicable in industry practice by: 1) eliminating the necessity for developing dedicated waste detection and segmentation algorithms for waste object localization, and 2) significantly reducing the time and costs required for adapting the solution to different use cases. With the proposed procedure, switching to a new waste type sorting is reduced to only two steps: The use of SAM for the automatic object extraction, followed by their separation into corresponding classes used to fine-tune the classifier. Validation on four use cases (floating waste, municipal waste, e-waste, and smart bins) shows robust results, with accuracy ranging from 86 to 97% when using the MobileNetV2 with SAM and FastSAM architectures. The proposed approach has a high potential to facilitate deployment, increase productivity, lower expenses, and minimize errors in robotic waste sorting while enhancing overall recycling and material utilization in the manufacturing industry.

Spillover effects of rural residents’ past pro-environmental production behavior on their voluntary waste separation behavior

Based on the survey data of rural residents in the National Ecological Civilization Pilot Area (Jiangxi), this paper empirically analyzes the spillover effect and mechanism of past pro-environmental production behavior on rural residents’ voluntary garbage sorting behavior, and adopts the fsQCA to clarify the grouping paths and examines the interactive relationship among multiple factors. The results of the empirical study show that: firstly, past pro-environmental production behaviors can directly promote rural residents’ voluntary garbage sorting behaviors; secondly, environmental self-identification and subjective norms have a partially mediating effect; thirdly, publicity and village regulations play a positive moderating effect. Further, the results of fsQCA analysis reaffirm the influence mechanisms, and reveal the multiple concurrent pathways through which past pro-environmental production behaviors drive the active waste sorting behaviors of rural residents. It’s found that there is a substitution relationship between rural residents’ past pro-environmental production behavior and publicity and education. This study enriches the theoretical explanation of the spillover of residents’ pro-environmental behaviors, and provides useful ideas for stimulating rural residents’ enthusiasm in active participation of rural residents in household waste sorting.

Influence of tin on crystallization processes in iron-carbon alloys (review)

Currently, iron foundries and production facilities are experiencing great difficulties in providing such an integral charge material for smelting cast iron as high-quality unalloyed steel scrap. Due to the fact that press and forging industries and enterprises are increasingly using high-strength steels to produce their products, which significantly reduce the weight of the products obtained, microalloyed with such elements-carbidizing agents as, for example, Mo, W, Nb, V, Ti, B, the charge yards of iron foundries are supplied waste “infected” with these elements. As a rule, in such industries, products are made from several grades of steels, both microalloyed with carbide-forming elements and without them, and due to the objective complexity, the waste sorting process is not organized organizationally, therefore, waste from all available grades of steel falls uncontrollably into steel bags, mixing in arbitrary proportions. In addition to carbide-forming elements, surfactants such as Cu, Sn, As and Sb are also the most common residual elements in steel and cast iron scrap. If the accumulation of carbide-forming elements to a certain extent can be considered a positive factor, then the accumulation of surfactants, which are practically impossible to remove from steel and cast iron, has a sharply negative effect on the mechanical and operational properties of iron-carbon alloys. Tin is used as an alloying element to produce both steels and cast irons with a fully pearlitic matrix. The addition of tin in an amount of no more than 0.10–0.15% seems to be the only practical way to avoid the growth of ferrite in a stable eutectoid reaction and completely transform the metal base of steel and cast iron into pearlite in a metastable eutectoid Fe–C system. At the same time, the question of how tin affects eutectoid transformations in steels and cast irons and, in general, the entire cycle of structure formation, is still a matter of debate. In this paper, an overview of the Fe–Sn system is performed, as well as experimental and industrial data available in the literature on the Fe–C–Sn system to assess the effect of tin on crystallization processes in iron-carbon alloys.

Strategi Pengelolaan Sampah Sistem Zero Waste Di Kelurahan Pegesangan Kota Mataram

This study aims to analyze the concept of zero waste, identify effective implementation strategies, assess the chances of success and establish an integrated waste management model for implementation in Pegesangan Village, Mataram City. This study uses descriptive and qualitative methods. The data sources for this study are primary data obtained directly from the government, private sector, universities, the community and information media. In addition, it is supported by secondary data obtained from documents, publications or literature related to zero waste system waste management strategies. The results of this study indicate that the lack of public awareness of the importance of waste management and the existence of traditional markets hinder the effectiveness of waste management and sorting, making it difficult to implement a zero-waste system in the Pegesangan Barat Village area. To overcome these obstacles, the Pegesangan Village Government implemented a "waste sorting" program between organic and inorganic waste. With proper waste separation, organic waste can be processed into useful compost and inorganic waste can be recycled or managed more efficiently. Therefore, community and government involvement is needed to create a waste management plan with a zero waste system, protect the environment, and produce benefits and economic value from the waste produced.

Prototype of AI-powered assistance system for digitalisation of manual waste sorting.

Global waste generation is projected to reach 3.40 billion tons by 2050, necessitating improved waste sorting for effective recycling and progress toward a circular economy. Achieving this transformation requires higher sorting intensity through intensified processes, increased efficiency, and enhanced yield. While manual sorting remains common, smaller plants often use positive sorting to recover recyclables, and larger plants combine automated systems with manual sorting. Negative sorting is employed to remove impurities and improve material quality. However, innovation in manual sorting has stagnated. Advances in Machine Learning and Artificial Intelligence offer transformative potential for waste management, with digitalisation and improved recyclate quality becoming priorities. Despite these trends, manual sorting is still largely treated as a digital black box. The presented research outlines the design of a novel, human-centric AI-powered assistance system to support sorting workers by enhancing decision-making and real-time assistance during the sorting process, driving the digitalisation of manual sorting. Potential use cases, system requirements, and essential components were explored. High-quality use case-specific data is essential for model training. Therefore, publicly available datasets were evaluated but found inadequate, necessitating use-case-specific data acquisition through near-industry-scale experiments. This data was used to train and develop key system components, such as object recognition, classification, and action recognition models. Results indicate that transfer learning with a balanced dataset is effective for waste-sorting applications. The classification model achieved 81% accuracy on an experimental acquired balanced dataset, outperforming the accuracy of the pre-trained model on its original dataset.

TRANSFORMASI PENGELOLAAN SAMPAH RUMAH TANGGA : PENDEKATAN ZERO WASTE MENUJU PERUBAHAN PERILAKU BERBASIS LINGKUNGAN

The problem of household waste management is one of the pressing environmental issues in various countries, including Indonesia. The high volume of waste that is not properly processed contributes to environmental pollution, such as soil, water, and air pollution. Tasik Rejo Village is one of the villages that focuses on waste management, this village has a BUMDes that is active in waste management but is only piled up at the TPS. Through Community Service activities, the service team carries out activities to change waste so that it can be utilized properly. The purpose of this service is to provide education and skills to Tasik Rejo village residents about the importance of maintaining environmental sustainability and a healthy lifestyle through waste processing, one of which is into fertilizer, so that waste can have value that can be utilized. This service method uses the ABCD method where the community plays an active role in every stage. Based on the results of the service, it can be said that the community is not fully aware of the importance of sorting waste, therefore further assistance is needed, but this service activity has a positive influence on changes in healthy living behavior in the community.

Pemberdayaan Masyarakat melalui Inisiatif Pengadaan “Keranjang Sedekah Sampah” dan “Budidaya Maggot” untuk Pelestarian Lingkungan

This community empowerment activity aims to increase awareness and involvement of youth and mothers in systematic waste management, as well as to realize a structured waste management strategy through the "Keranjang Sedekah Sampah" and "Maggot Cultivation" initiatives. This activity is carried out by providing socialization to provide basic knowledge about waste management, workshops to train practical skills such as waste sorting and maggot cultivation, mentoring to ensure effective program implementation, and evaluation to assess the success and sustainability of the program in the community. The results of this community service activity show the enthusiasm of participation, especially from mothers, in sorting waste and adopting maggot cultivation as a solution to organic waste management. This community service activity also succeeded in establishing "Keranjang Sedekah Sampah" points and a pilot site for "Maggot Cultivation". However, youth participation still needs to be improved, and there are challenges in the form of resistance to maggot cultivation. This program significantly improved the community's understanding of sustainable waste management, but further efforts are needed to increase youth involvement and optimize the program's sustainability

Design and Construction of Magnetic Support Construction Separator on Track V 33 BC-5 at Greenzone 2

The process of shredding and sorting waste in the Pre Processing method is one of PT Solusi Bangun Indonesia's contributions in overcoming waste and pollution problems. The waste will be shredded into certain sizes and put into the cement kiln. The processing place is called a green zone. In this process, sometimes the material transport contains impurities in the form of metal and the like. This distribution has the potential to cause foreign material to be carried because there is no sorting of waste content. Belt conveyors and dynamic disc screens are often damaged by the metal material. This problem can be overcome with a magnetic separator to separate foreign metals from waste that is channeled using a belt conveyor. The magnetic separator provides protection for the dynamic disc screen and conveyor operating process from foreign material so that the potential for wear on the dynamic disc screen and torn belt conveyor can be avoided. The installation of the magnetic separator position uses a construction based on the optimal position. This study discusses the design and construction of the green zone belt conveyor magnetic separator installation. The construction installation for the magnetic separator aims to facilitate access to maintenance and cleaning, also provide access to dispose of foreign materials and protect the material transport system in the green zone. Before redesign magnetic sparator, the company spent Rp. 389,000,000 maintenance cost from November 2023 to February2024 period. After redesign, it’s can reducing maintenance and repair costs during the period March 2024 to July 2024 with no maintenance related to metal separation.

Promoting Sustainability in the Recycling of End-of-Life Photovoltaic Panels and Li-Ion Batteries Through LIBS-Assisted Waste Sorting

To promote sustainability and reduce the ecological footprint of recycling processes, this study develops an analytical tool for fast and accurate identification of components in photovoltaic panels (PVs) and Li-Ion battery waste, optimizing material recovery and minimizing resource wastage. The laser-induced breakdown spectroscopy (LIBS) technique was selected and employed to identify fluoropolymers in photovoltaic back sheets and to determine the thickness of layers containing fluorine. LIBS was also used for Li-Ion batteries to reveal the elemental composition of anode, cathode, and separator materials. The analysis not only revealed all the elements contained in the electrodes but also, in the case of cathode materials, allowed distinguishing a single-component cathode (cathode A containing LiCoO2) from multi-component materials (cathode B containing a mixture of LiMn2O4 and LiNi0.5Mn1.5O4). The results of LIBS analysis were verified using SEM-EDS analysis and XRD examination. Additionally, an indirect method for identifying fluoropolymers (polytetrafluoroethylene (PTFE) or poly(vinylidene fluoride) (PVDF)) employed to prepare dispersions of cathode materials was proposed according to the differences in wettability of both polymers. By enabling efficient material identification and separation, this study advances sustainable recycling practices, supporting circular economy goals in the renewable energy sector.

Pengaruh Literasi Keuangan Terhadap Orientasi Kewirausahaan Sosial dan Kinerja Usaha Bank Sampah di Yogyakarta

The condition of waste management in Indonesia, including in Yogyakarta, is becoming an increasingly complex problem along with increasing population and urbanization. Public awareness of the importance of waste sorting and management is also still low, even though the city government has attempted various programs related to 3R-based waste management (Reduce, Reuse, Recycle). The waste bank in Yogyakarta is one of the innovative efforts developed to overcome the waste problem and provide economic value from the waste produced by the community. The waste bank in Yogyakarta is a model of social entrepreneurship. With good management, waste banks can function as local economic centers that generate income from waste processing by incorporating the concept of social entrepreneurship orientation. Financial literacy has a very important role in supporting waste bank operations, especially in developing social entrepreneurial orientation and improving their performance. Waste banks, as entities that manage waste with social and environmental goals, must also manage finances well to ensure sustainability and a wider positive impact. The sampling technique uses saturated samples. Analytical tools This research uses descriptive analysis techniques and quantitative analysis techniques with structural equation models or Structural Equation Modeling (SEM), especially Partial Least Square (PLS). The results of this research are 1) Financial Literacy has no effect on waste bank business performance; 2) Social Entrepreneurship Orientation has a positive effect on waste bank business performance; 3) Social Entrepreneurship Orientation fully mediates the relationship between Financial Literacy and waste bank business performance

Analysis of Pro-Environmental Behavior of Residents In Household Waste Management

The waste problem in Indonesia is one of the major problems. Bogor City is one of the cities that has a serious waste problem. Public awareness and participation are needed to overcome the waste problem. Waste management at the Rangga Mekar Waste Bank is important for good waste management by sorting waste. Public participation in waste sorting practices is expected to reduce environmental pollution. This study aims to see the Rangga Mekar waste bank program educating and influencing the community by analyzing the influence of environmental factors of the Rangga Mekar Waste Bank on the personal factors of waste bank customers, analyzing the influence of environmental factors of the Rangga Mekar Waste Bank on the behavior of residents in managing waste, and the influence of personal factors of residents on waste management behavior. The method used in this study is the survey method. The results show that environmental factors have a positive influence in measuring personal constructs, but the influence of direct environmental factors on behavior is not significant. Personal factors have a positive influence on behavioral factors. Waste management in the community is greatly influenced by personal factors and individual self-ability. The environment acts as a reinforcer, while behavioral change depends on improving personal factors.