Search Results (70)

Surface stain contamination poses a critical barrier to the automated, high-precision fiber identification required for industrial-scale waste textile recycling. In this study, a dataset comprising 120 physical specimens (yielding 1200 regions of interest, ROIs) across 12 contamination categories was constructed by contaminating cotton, polyester, and poly-cotton blend textiles with carbon black, protein, and oil stains. The spectral interference effects of stains—including baseline drift and spectral overlapping induced by physical shielding and chemical absorption—were systematically analyzed. To identify the optimal classification pipeline, three mathematical preprocessing methods (First Derivative, FD; Standard Normal Variate, SNV; and Multiplicative Scatter Correction, MSC) were evaluated alongside Support Vector Machine (SVM) and One-Dimensional Convolutional Neural Network (1D-CNN) models. Results show that among the SVM-based pipelines, the FD-SVM model effectively resolves overlapping absorption peaks, achieved an average accuracy of 98.17% ± 1.33%, but remains highly dependent on mathematical preprocessing. In contrast, the 1D-CNN model employing a progressive stacking architecture of multi-scale convolutional kernels attains a highly robust mean accuracy of 99.58% ± 0.56% under a strict specimen-level 10-fold cross-validation. It achieves this by directly utilizing radiometrically calibrated raw spectra, thereby effectively bypassing manual spectral feature engineering. These findings demonstrate that Hyperspectral Imaging coupled with end-to-end deep learning provides a feasible and industrially deployable solution for simultaneous stain detection and fiber identification in waste textile sorting. Full article

Deep learning has emerged as an effective tool for automatic waste classification, supporting cleaner cities and more sustainable recycling systems. Because environmental protection is central to the United Nations Sustainable Development Goals (SDGs), improving the sorting and processing of everyday waste is a practical step toward this broader objective. In many real-world settings, however, waste is still sorted manually, which is slow, labor-intensive, and prone to human error. Although convolutional neural networks (CNNs) can automate this task with high accuracy, many state-of-the-art models remain too large and computationally demanding for low-cost edge devices intended for deployment in homes, schools, and small recycling facilities. In this work, we investigate lightweight waste-classification models suitable for TinyML deployment while preserving competitive accuracy. We first benchmark multiple CNN architectures to establish a strong baseline, then apply complementary compression strategies including quantization, pruning, singular value decomposition (SVD) low-rank approximation, and knowledge distillation. In addition, we evaluate an RL-guided multi-teacher selection benchmark that adaptively chooses one teacher per minibatch during distillation to improve student training stability, achieving up to 85% accuracy with only 0.496 M parameters (FP32 ≈ 1.89 MB; INT8 ≈ 0.47 MB). Across all experiments, the best accuracy–size trade-off is obtained by combining knowledge distillation with post-training quantization, reducing the model footprint from approximately 16 MB to 281 KB while maintaining 82% accuracy. The resulting model is feasible for deployment on mobile applications and resource-constrained embedded devices based on model size and TensorFlow Lite Micro compatibility. Full article

The widespread utilization of plastic materials across various industrial sectors drives a continuous increase in global polymer demand. The exponential production growth generates severe environmental challenges regarding municipal solid waste management, as substantial fractions of post-consumer residuals enter landfills due to limited recycling infrastructure. Mitigating the global environmental burden requires the implementation of advanced recovery strategies to transition polymer waste into viable secondary feedstocks. Consequently, deploying efficient sorting techniques constitutes a fundamental requirement to integrate plastic materials into formal waste management protocols and optimize recycling yields. Technological innovations currently drive the transition from traditional manual segregation towards highly sophisticated automated sensor-based sorting architectures, maximizing separation efficiency. In this context, the present study comprehensively reviews pretreatment classification techniques engineered to fractionate heterogeneous waste streams into high-purity material flows. Rather than restricting the analysis to polyolefins, this review encompasses a broad spectrum of commodity polymers predominantly found in urban solid waste environments. Full article

Growing amounts of municipal waste and the need for efficient recycling demand automated and accurate classification systems. This paper investigates deep learning approaches for multi-class waste sorting based on image data, comparing three widely used convolutional neural network architectures (ResNet-50, EfficientNet-B0, and MobileNet V3) with a custom hybrid model (CustomNet). The dataset comprises 13,933 RGB images across 10 waste categories, combining publicly available samples from the Kaggle Garbage Classification dataset (61.1%) with images collected in house (38.9%). The three glass sub-categories (brown, green, and white glass) were merged into a single glass class to ensure consistent class representation across all dataset splits. Preprocessing steps include normalization, resizing, and extensive data augmentation to improve robustness and mitigate class imbalance. Transfer learning is applied to pretrained models, while CustomNet integrates feature representations from multiple backbones using projection layers and attention mechanisms. Performance is evaluated using accuracy, macro-F1, and ROC–AUC on a held-out test set. Statistical significance was assessed using paired t-tests and Wilcoxon signed-rank tests with Bonferroni correction across five-fold cross-validation runs. The results show that CustomNet achieves 97.79% accuracy, a macro-F1 score of 0.973, and a ROC–AUC of 0.992. CustomNet significantly outperforms EfficientNet-B0 and MobileNet V3 ($p<0.001$, Bonferroni corrected), and it achieves performance parity with ResNet-50 ($p=0.383$) at a substantially lower parameter count in the classification head (9.7 M vs. 25.6 M). These findings indicate that combining multiple feature extractors with attention mechanisms improves classification performance, supports qualitative model explainability via saliency visualization (Grad-CAM), and enables practical deployment on heterogeneous Edge AI platforms. Inference benchmarking on an NVIDIA Jetson Orin Nano demonstrated real-world deployment feasibility at 86.70 ms per image (11.5 FPS). Full article

Construction and demolition waste (CDW) represents a critical environmental challenge in the building sector, with global generation exceeding 3.57 billion tonnes annually. The circular economy (CE) framework offers a transformative pathway through selective deconstruction and material recovery, yet implementation faces significant barriers including information asymmetry, supply chain fragmentation, and regulatory uncertainty. This study conducts a systematic literature review using the Context–Mechanism–Outcome (CMO) framework to analyze how computational methods, specifically Digital Twins (DT), Building Information Modeling (BIM), Internet of Things (IoT), blockchain, artificial intelligence, and robotics, act as enablers for resilience in CDW management. Following PRISMA 2020 guidelines and realist synthesis principles, we analyzed 42 high-quality empirical studies from Web of Science and Scopus (2015–2025). Our analysis identifies seven primary mechanisms: traceability (M1), simulation (M2), classification (M3), tracking (M4), collaboration (M5), analytics (M6) and robotics (M7). These mechanisms interact with four critical contexts (information asymmetry, supply chain fragmentation, economic uncertainty, operational risks) to generate outcomes at two levels: resilience capabilities (visibility, monitoring, collaboration, flexibility, anticipation) and performance indicators (recovery rates, cost reduction, CO₂ emissions mitigation, occupational safety). Key findings from the CMO analysis reveal that blockchain-enabled traceability increases material recovery rates by 15–25%, DT simulation reduces deconstruction costs by 20–30%, and computer vision automation improves sorting accuracy to 85–95%. The study contributes middle-range theories explaining how digital technologies enable circular transitions under specific contextual conditions, offering actionable strategic implications for researchers, project managers, technology developers, and policymakers committed to advancing computational economics in sustainable construction. Full article

With the rapid expansion of the global textile sector and increasing awareness of the environmental pollution caused by textile waste, enhancing the recycling of textile waste has become essential to reduce the volume of materials sent to landfill or incineration. As recycling technologies advance, automated sorting systems that are capable of handling large waste streams and accurately identifying materials for appropriate recycling pathways are increasingly recognised as being critical for efficient textile-waste management. Since 2015, over 20 studies have specifically explored technologies and strategies for automating textile sorting of textile wastes. This mini review introduces various textile fibre identification technologies, including traditional visual and tactile examination; label checking and modern identification technology; and NIR, FT-IR, RFID tags. It summarises the current state of sorting processes, with particular emphasis on the development of AI-assisted, fibre-type-based sorting technologies. Commercial scale automated sorting is not established yet for textile waste recycling, due to the complexity of materials used in textiles, the equipment identification limits and high cost of processing, while machine learning and artificial neural networks provide opportunities for future research advancement and commercialisation. Full article

Glass is a highly recyclable material that provides substantial environmental benefits, including savings in raw materials and energy as well as a reduction in CO₂ emissions. To ensure the production of high-quality secondary raw materials, container glass from municipal waste separate collection must be accurately separated by color in recycling plants, where only minimal color mixing is tolerated. Color sorting is therefore a key step in glass recycling, as it directly affects both the quality and the market value of recycled cullet. Given the increasingly stringent color quality requirements for recycled glass and the high fraction of cullet used in container glass, advanced technological solutions are needed to improve sorting accuracy. In this study, a visible–near-infrared (VIS-NIR: 400–1000 nm) hyperspectral imaging (HSI) approach integrated with machine learning (ML) is proposed for the automated classification of post-consumer glass fragments from bottles and jars into five color categories: brown, dark green, light green, half-white and white. A hierarchical Partial Least Squares-Discriminant Analysis (PLS-DA) model combined with an object-based analysis strategy was developed to optimize color recognition. The proposed system achieved sensitivity and specificity values between 0.910 and 1.000, demonstrating excellent robustness and predictive capability. Validation on independent datasets confirmed the model’s reliability, with all color glass fragments correctly classified at the object level. The results highlight the potential of HSI-ML systems to enhance color sorting accuracy and process efficiency in recycling plants, contributing to improved material recovery and the advancement of sustainable, circular glass production. Full article

A method for simultaneous classification of fabric material and color based on hyperspectral imaging and visual detection is proposed. Fabric material classification is performed using hyperspectral imaging (HSI) combined with a one-dimensional convolutional neural network (1D-CNN), while fabric color recognition is achieved using an red-green-blue (RGB) camera and a color classification model. Material and color features from the same fabric sample are matched to realize synchronous classification. Experiments were conducted on three fabric materials (cotton, polyester, and cotton–polyester blend) and eight colors. At a conveyor speed of 1 m/s, the sorting success rates reach 95.0% for cotton, 97.5% for polyester, and 85.0% for cotton–polyester blended fabrics. The proposed method demonstrates reliable performance for single-material fabrics and good industrial applicability for automated fabric sorting. Full article

Automated waste classification is essential for improving recycling efficiency and supporting sustainable waste management systems. However, conventional convolutional neural network (CNN) approaches primarily focus on localized feature extraction, which may limit their ability to capture complex spatial relationships in heterogeneous waste materials. This study proposes DeepWasteSort-SI-SSO, a Vision Transformer (ViT)-based framework enhanced with a Self-Improved Sparrow Search Optimization (SI-SSO) strategy for hyperparameter tuning. The optimization process focuses on key training parameters, including learning rate, batch size, and dropout rate, to improve convergence stability and reduce the risk of suboptimal local minima. The framework was evaluated on a balanced four-class waste image dataset (paper, wood, food, and leaves; N = 4000) using a five-fold cross-validation protocol. Experimental results achieved an average accuracy of 95.5% (±0.007), a macro-averaged AUC-ROC of 0.975, and a Cohen’s Kappa coefficient of 0.938, indicating strong agreement between predicted and true labels. Comparative experiments against ResNet-50 and a baseline ViT configuration suggest that SI-SSO optimization improves performance stability with only a modest increase in computational cost. These findings highlight the potential of optimized Transformer-based approaches for automated waste image classification under controlled evaluation conditions. Full article

Construction and Demolition Waste (CDW) management represents a growing global challenge due to the large volume and heterogeneous nature of materials involved. This study addresses this issue by developing an automated classification system based on computer vision and deep learning, aiming to enhance efficiency and sustainability compared to manual sorting methods. A representative dataset was collected in a recycling facility, and multiple convolutional architectures were evaluated, with ResNet50 employing transfer learning achieving the best performance. The model was integrated into a web-based prototype capable of processing both still images and real-time video, offering visualization and interpretability tools for users. In addition to performance evaluation, the system’s cybersecurity and resilience were analyzed, focusing on data integrity, secure model deployment, and robustness against potential cyber threats. Experimental results demonstrate competitive classification accuracy and stable operation under realistic conditions. The study confirms the technical feasibility of the approach and emphasizes the importance of incorporating cybersecurity considerations into AI-driven industrial solutions, establishing a foundation for secure, scalable, and sustainable CDW management systems. Full article

The escalating accumulation of waste printed circuit boards (WPCBs) underscores the urgent need for efficient recovery of valuable resources. Notably, WPCBs harbor a considerable number of intact electronic components that remain functional or could be repurposed. Nevertheless, the automated recognition and sorting of these components remain highly challenging, owing to their miniature dimensions, diverse model types, and the absence of publicly available, high-quality datasets. To address these challenges, this paper introduces a novel image dataset of discarded electronic components and proposes a deep learning-based data augmentation model that combines classical augmentation methods with DCGAN and SRGAN to achieve dataset size augmentation. This paper further conducts Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) evaluation on the generated images to ensure their suitability for downstream classification tasks. Experimental results demonstrate significant improvements in classification accuracy, with AlexNet, VGG19, ResNet18, ResNet101, and ResNet152 achieving increases of 6.6%, 9.7%, 4%, 5.4%, and 6.2%, respectively, compared to classical augmentation. This method enables precise identification to facilitate the downstream recovery of intact electronic components, thereby contributing to the conservation of natural resources and the effective mitigation of environmental pollution. Full article

Plastic waste in river systems represents a major pathway of marine pollution, with rivers estimated to contribute up to 80% of the plastic entering the ocean. This study introduces a deep learning framework with preprocessing for automated detection and tracking of floating plastic waste (macroplastics) in the urban canals of the Chao Phraya River, Thailand. Unlike previous approaches that rely on site-specific retraining or model modification, our method employs a YOLO-based detection model integrated with DeepSORT (Deep Simple Online and Realtime Tracking). The model, initially trained on laboratory flume images, was adapted to real river conditions through a three-step preprocessing pipeline comprising skew correction, background removal, and object region extraction. Experiments on 2000 canal images demonstrated that preprocessing improved the mean Average Precision (mAP) from 0.74 to 0.85, with notable gains for categories such as foam and paper. Testing with a more advanced YOLO architecture further enhanced accuracy, indicating that preprocessing and model upgrades are complementary. These findings suggest that reliable detection and quantification of floating waste can be achieved without retraining. The proposed framework provides a scalable and cost-effective solution for monitoring in data-limited regions, contributing to efforts to mitigate riverine and marine plastic pollution. Future work will address the remaining limitations, as detection performance is still influenced by strong reflections, motion blur, and occlusion, occasionally resulting in missed detections. Full article

The application of efficient optical-electrical sorting technology for the automatic separation of copper mine waste rocks not only enables the recovery of valuable copper metals and promotes the resource utilization of non-ferrous mine waste, but also conserves large areas of land otherwise used for waste disposal and alleviates associated environmental issues. However, the process is challenged by the low copper content, fine dissemination of copper-bearing minerals, and complex mineral composition and associated relationships. To address these challenges, this study leverages dual-energy X-ray imaging and multimodal learning, proposing a lightweight twin-tower convolutional neural network (CNN) designed to fuse high- and low-energy spectral information for the automated sorting of copper mine waste rocks. Additionally, the study integrates an emerging Kolmogorov-Arnold network as a classifier to enhance the sorting performance. To validate the efficacy of our approach, a dataset comprising 31,057 pairs of copper mine waste rock images with corresponding high- and low-energy spectra was meticulously compiled. The experimental results demonstrate that the proposed lightweight method achieves competitive, if not superior, performance compared to contemporary mainstream deep learning networks, yet it requires merely 1.32 million parameters (only 6.2% of ResNet-34), thereby indicating extensive potential for practical deployment. Full article

Effective waste management is important for reducing environmental harm, improving recycling operations, and building urban sustainability. However, accurate waste classification remains a critical challenge, as many deep learning models struggle with diverse waste types. In this study, classification accuracy is enhanced using transfer learning, ensemble techniques, and custom architectures. Eleven pre-trained convolutional neural networks, including ResNet-50, EfficientNet variants, and DenseNet-201, were fine-tuned to extract meaningful patterns from waste images. To further improve model performance, ensemble strategies such as weighted averaging, soft voting, and stacking were implemented, resulting in a hybrid model combining ResNet-50, EfficientNetV2-M, and DenseNet-201, which outperformed individual models. In the proposed system, two specialized architectures were developed: EcoMobileNet, an optimized MobileNetV3 Large-based model incorporating Squeeze-and-Excitation blocks for efficient mobile deployment, and EcoDenseNet, a DenseNet-201 variant enhanced with Mish activation for improved feature extraction. The evaluation was conducted on a dataset comprising 4691 images across 10 waste categories, sourced from publicly available repositories. The implementation of EcoMobileNet achieved a test accuracy of 98.08%, while EcoDenseNet reached an accuracy of 97.86%. The hybrid model also attained 98.08% accuracy. Furthermore, the ensemble stacking approach yielded the highest test accuracy of 98.29%, demonstrating its effectiveness in classifying heterogeneous waste types. By leveraging deep learning, the proposed system contributes to the development of scalable, sustainable, and automated waste-sorting solutions, thereby optimizing recycling processes and minimizing environmental impact. Full article

This paper presents a comprehensive sensitivity analysis of the pioneering real-world deployment of computer vision-enabled construction waste sorting in Finland, implemented by a leading provider of robotic recycling solutions. Building upon and extending the findings of prior field research, the study analyzes an industry flagship case to examine the financial feasibility of computer vision-enabled robotic sorting compared to conventional sorting. The sensitivity analysis covers cost parameters related to labor, wages, personnel training, machinery (including AI software, hardware, and associated components), and maintenance operations, as well as capital expenses. We further expand the existing cost model by integrating the net present value (NPV) of investments. The results indicate that the computer vision-enabled automated system (CVAS) achieves cost competitiveness over conventional sorting (CS) under conditions of higher labor-related costs, such as increased headcount, wages, and training expenses. For instance, when annual wages exceed EUR 20,980, CVAS becomes more cost-effective. Conversely, CS retains cost advantages in scenarios dominated by higher machinery and maintenance costs or extremely elevated discount rates. For example, when the average machinery cost surpasses EUR 512,000 per unit, CS demonstrates greater economic viability. The novelty of this work arises from the use of a pioneering real-world case study and the improvements offered to a comprehensive comparative cost model for CVAS and CS, and furthermore from clarification of the impact of key cost variables on solution (CVAS or CS) selection. Full article