Article
Computer Science, Information Systems
Zhiying Tan, Zhongwen Fei, Baolai Zhao, Jian Yang, Xiaobin Xu, Zilong Wang
Summary: A new method for identifying PET plastic bottles based on polarization vision is proposed to improve the purity of PET recycling. By segmenting the region of plastic bottle location and extracting features, the research aims to enhance the material identification process.
Article
Computer Science, Information Systems
Subhajit Chatterjee, Debapriya Hazra, Yung-Cheol Byun
Summary: This study proposes an automated transparent plastic bottle classification system to replace traditional waste disposal methods. By utilizing Transfer Learning (TL) and Ensemble Learning (EL) techniques, and applying data augmentation, the system is able to accurately classify and identify transparent plastic bottle images. This method has significant potential value for environmental protection and pollution control.
Article
Environmental Sciences
Guangxin Liu, Liguo Wang, Danfeng Liu, Lei Fei, Jinghui Yang
Summary: This article proposes a non-parallel SVM model, which improves the classification effect and generalization performance for hyperspectral images by adding an additional empirical risk minimization term and bias constraint.
Article
Environmental Sciences
Yamila V. Vazquez, Luciana A. Castillo, Silvia E. Barbosa
Summary: This study proposes a rethinking of plastic rigid shampoo bottles based on Design for the Environment concepts. By assessing the weight/capacity ratio and compression mechanical properties of different shampoo brands, it was confirmed that there is an oversizing of bottles and excessive use of materials for aesthetic purposes. The study recommends using a single material for the bottles and suggests that HDPE is a suitable choice due to its ability to make all bottle parts, recyclability, and low price/performance relationship. From a marketing perspective, a proper ecodesign can shift the focus from aesthetics to sustainability in line with current consumer environmental awareness.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Lili Zhu, Petros Spachos
Summary: Food quality and safety are crucial for human health and social stability. This study proposed a mobile visual system to grade bananas, achieving high accuracy rates in the grading process. The complex process of ensuring food quality involves all stages from cultivation to consumption.
INTERNET OF THINGS
(2021)
Article
Engineering, Electrical & Electronic
Kane C. Williams, Michael D. O'Toole, Anthony J. Peyton
Summary: The need for material recovery and recycling in building a circular economy is a global imperative. Nonferrous metals, highly recyclable, present a challenge in separating them into recyclable groups. Magnetic induction spectroscopy (MIS) was proposed to discriminate between nonferrous metals by measuring how a metal fragment scatters a magnetic field. MIS combined with machine learning achieved high purity and recovery rates for different metal groups, with the exception of a waste stream containing aluminum alloys where the introduction of color substantially improved results. The random forest (RF), extra trees, and support vector machine (SVM) algorithms consistently performed the best.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Ceren Atik, Recep Alp Kut, Reyat Yilmaz, Derya Birant
Summary: This paper proposes a novel method called support vector machine chains (SVMC) that involves chaining together multiple SVM classifiers in a special structure, decrementing one feature at each stage. The paper also introduces a new voting mechanism called tournament voting, where classifiers' outputs compete in groups and the winning class label of the final round is assigned as the prediction. Experimental results show that SVMC outperforms SVM in terms of accuracy and achieves a 6.88% improvement over state-of-the-art methods.
Review
Engineering, Environmental
Spyridoula Gerassimidou, Paulina Lanska, John N. Hahladakis, Elena Lovat, Silvia Vanzetto, Birgit Geueke, Ksenia J. Groh, Jane Muncke, Maricel Maffini, Olwenn V. Martin, Eleni Iacovidou
Summary: This study provides a systematic evidence map of the migration of chemicals from PET drink bottles into food, highlighting the challenges and influential factors. While recycling PET bottles is vital for reducing plastic pollution, safety and quality concerns may arise.
JOURNAL OF HAZARDOUS MATERIALS
(2022)
Article
Chemistry, Multidisciplinary
Janghee Choi, Byeongju Lim, Youngjun Yoo
Summary: Plastic waste management is a significant environmental issue due to the improper disposal and mismanagement of plastic waste. This paper presents an approach that utilizes image sensors and the You Only Look Once (YOLO) model to enhance the classification of plastic waste based on its shape. The results demonstrate the effectiveness and scalability of the system, achieving a high classification accuracy rate between chemically similar samples. The proposed approach contributes to a more sustainable and efficient plastic waste management system, reducing the environmental impact of plastic waste and promoting a cleaner environment.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Environmental
Xiaozheng Chen, Nils Kroell, Malte Althaus, Thomas Pretz, Roland Pomberger, Kathrin Greiff
Summary: This study aims to investigate the impact of shrink sleeves on the mechanical recycling of plastic bottles and propose solutions to improve the sorting process. Using machine learning algorithms and NIR spectra data, the influences of different product designs and post-consumer effects on the classification process were studied. The results show that the sortability and mechanical recycling of sleeved bottles can be greatly enhanced by avoiding certain sleeve designs, incorporating sleeved bottle spectra into the training data, and selecting appropriate machine learning algorithms.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Mathematics
Guvenc Arslan, Ugur Madran, Duygu Soyoglu
Summary: In this paper, a novel classification approach is proposed by introducing a new clustering method as an intermediate step to discover the structure of a data set and reduce its size. Experimental results show that the proposed method performs comparably to standard support vector machines.
Article
Computer Science, Artificial Intelligence
Liming Liu, Maoxiang Chu, Rongfen Gong, Li Zhang
Summary: The improved nonparallel support vector machine (INPSVM) proposed in this article inherits the advantages of nonparallel support vector machine (NPSVM) while also offering incomparable benefits over twin support vector machine (TSVM). INPSVM effectively eliminates noise effects and achieves higher classification accuracy for both linear and nonlinear datasets compared to other algorithms. Experimental results demonstrate the superior efficiency, accuracy, and robustness of INPSVM.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Biotechnology & Applied Microbiology
Ke-Fan Wang, Jing An, Zhen Wei, Can Cui, Xiang-Hua Ma, Chao Ma, Han-Qiu Bao
Summary: In this paper, a novel imbalance classification method based on deep learning and fuzzy support vector machine, named DFSVM, is proposed. The method utilizes a deep neural network to obtain an embedding representation of the data and performs oversampling in the embedding space to address the data imbalance issue. Furthermore, a fuzzy support vector machine is used as the final classifier to improve the classification quality of minority classes.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Operations Research & Management Science
M. A. Ganaie, M. Tanveer, Jatin Jangir
Summary: In this study, a novel universum twin support vector machine with pinball loss function (Pin-UTSVM) is proposed for the classification of EEG signals. The Pin-UTSVM model is more robust to noise compared to existing models and performs better in experimental results.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Ganesan Kalaiarasi, Sureshbabu Maheswari
Summary: In this study, an effective classification of hyperspectral images was modeled and simulated with the proximal support vector machine (PSVM) by integrating them with the deep learning approach. The new deep PSVM classifiers, designed to handle the complexity, discrepancies, and irregularities in traditional hyperspectral image classifiers, showed better classification accuracy compared to other techniques.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Environmental
Xiaojian Liu, Bei Wang, Yayun Ma, Xiangyang Zhou, Juan Yang, Yuehui He, Jingjing Tang, Fanyun Su, Wan Yang
Summary: This study proposes a combined process of reduction roasting of herb-medicine residue and oxalic acid leaching to improve the recovery efficiency of lithium from spent lithium-ion batteries. By utilizing the reducing gas produced from the pyrolysis of herb-medicine residue, the layered structure of the cathode powder is destroyed and converted into Li2CO3, Ni, Co, and MnO. Additionally, selective extraction of lithium is achieved using oxalic acid, and the efficiency and kinetics of lithium extraction are improved under the combined action of herb-medicine residue and oxalic acid.
Article
Engineering, Environmental
Muxina Konarova, Nuno Batalha, Gabriel Fraga, Mohamed H. M. Ahmed, Steven Pratt, Bronwyn Laycock
Summary: This study presents a proof of concept for a technology that integrates PET recovery from mixed plastic waste and plastic pyrolysis. By depolymerizing PET into TPA using a low volatility oil as medium, it achieves low-pressure operation and a selective separation and recovery of TPA from the product mix. Full PET conversion and high TPA recovery were achieved, making it an effective solution for processing mixed waste streams and improving the yield and quality of liquid product from thermal pyrolysis compared to untreated feedstock.
Article
Engineering, Environmental
Zhenhua Sun, Jing Li, Xuejiang Wang, Siqing Xia, Jianfu Zhao
Summary: This study investigated the influence of in-situ formed MgFe2O4 on the hydrothermal treatment of swine manure. The results showed that the in-situ formation of MgFe2O4 improved the dehydration and decarboxylation of organic components in swine manure, thereby improving its carbonization degree. Furthermore, it enhanced the stabilization of heavy metals and the retention of phosphorus. MgFe2O4 modified hydrochars exhibited remarkable adsorption capacity for Pb(II) and Cu(II) without any leaching of heavy metals.
Article
Engineering, Environmental
Yijing Jiang, Boyang Leng, Jingxin Xi
Summary: The increased generation of municipal solid waste has had a significant impact on the economy, environment, and public health. The current waste treatment process has limitations. By developing a comprehensive social costing model, this study assesses the impacts of municipal solid waste management throughout its life cycle and provides policymakers with best practices and feasibility information.
Article
Engineering, Environmental
Marina Hernandes de Paula e Silva, Ricardo Coser Mergulha, Jose Geraldo Vidal Vieira, Andrea Brasco Pampanelli, Rodrigo Salvador, Diogo Aparecido Lopes Silva
Summary: This study developed and implemented a self-assessment tool to assist companies in decision-making processes for establishing circular flows based on Lean Manufacturing and Circular Economy principles. The tool utilized a maturity model and was applied to nine companies of varying characteristics. The findings revealed that certain companies showed higher maturity in water-waste and chemical-emissions management, with larger enterprises focusing on these strategies. However, many companies lacked sufficient training and employee awareness prior to seeking cleaner alternatives, and comprehensive actions to manage the product lifecycle were lacking. To address these gaps, the tool provided tailored recommendations for each company to improve their processes, products, and value chain.
Article
Engineering, Environmental
Gamze Dogdu, Turgay Pekdemir, Sanaz Lakestani, Seyda Karabork, Osman Cavus
Summary: This paper presents data on food waste associated with mini size food packaging services, highlighting the difficulties in emptying the food and consumer wastefulness as the main causes. These findings have significant implications for the sustainability of food and relevant packaging.
Article
Engineering, Environmental
Qingxia Li, Xin Kong, Yuxin Chen, Jianan Niu, Jia Jing, Jin Yuan, Yifeng Zhang
Summary: This study investigates how to enhance methane production from food waste after hydrothermal pretreatment. The results demonstrate a significant increase in methane yield when zero-valent iron and magnetite are used together, and high organic loading is favorable for methane production. Microbial diversity analysis further reveals the dominant pathways and metabolic processes involved in methane generation.
Article
Engineering, Environmental
D. H. H. Sim, I. A. W. Tan, L. L. P. Lim, E. T. Lau, B. H. Hameed
Summary: The development of controlled-release fertilizer formulation is important for preventing environmental pollution caused by nutrient leaching and volatilization. This study combined biochar-based fertilizer with encapsulation technology to improve the nutrient release mechanism. Optimal conditions for synthesizing urea-impregnated biochar (UIB) were determined using central composite design, and the release of nitrogen was described by mathematical models. Results showed that encapsulated UIB (EUIB) achieved complete release of nitrogen in water and exhibited improved water retention in sandy-textural soil. Therefore, EUIB derived from peppercorn waste has the potential to be used as a sustainable controlled-release fertilizer for agriculture.
Article
Engineering, Environmental
Yuchuan Wang, Neslihan Akdeniz
Summary: Incorporating biochar into composting systems can increase compost temperatures. This study developed a heat transfer model for a biochar-amended co-composting system and found that biochar increased thermal conductive losses but also enhanced microbial activity, resulting in an overall increase in total heat unit. When biochar was applied on the surface, it mainly functioned as an insulator.
Article
Engineering, Environmental
George Tsalis, Birger Boutrup Jensen, Jessica Aschemann-Witzel
Summary: This paper empirically explores the relationship between retail price promotions and household food waste. The results show that households with a higher proportion of discount food purchases and environmental awareness tend to waste less food, while larger households and those lacking food handling skills tend to waste more food.
Article
Engineering, Environmental
Lukas Friederici, Arne Koch, Patrick Martens, Jana Pantzke, Sebastiano Di Bucchianico, Thorsten Streibel, Christopher P. Rueger, Ralf Zimmermann
Summary: The increasing demand for lightweight materials has led to a rise in fiber-reinforced plastic (FRP) production. However, the properties and compositional range of FRPs pose challenges to recycling strategies. Pyrolysis has emerged as a promising method for separating the fibers from the polymer matrix. This study investigated the pyrolysis process using thermal analysis and high-resolution mass spectrometry, and also assessed the toxicity of the recovered fibers using an in vitro model.
Review
Engineering, Environmental
Devika Kannan, Shakiba Khademolqorani, Nassibeh Janatyan, Somaieh Alavi
Summary: This paper introduces Smart Waste Management (SWM) that applies Industry 4.0 technologies in waste management. A framework called SWM4.0 is developed, which highlights the importance of smart people, smart cities, smart enterprises, and smart factories in achieving successful waste management. The paper also suggests future research directions and managerial implications.