Search Results (76)

Automated waste classification is an essential step toward efficient recycling and waste management. Traditional deep learning models, such as convolutional neural networks, rely on extensive labeled datasets to achieve high accuracy. However, the annotation process is labor-intensive and time-consuming, limiting the scalability of these approaches in real-world applications. Zero-shot learning is a machine learning paradigm that enables a model to recognize and classify objects it has never seen during training by leveraging semantic relationships and external knowledge sources. In this study, we investigate the potential of zero-shot learning for waste classification using two vision-language models: OWL-ViT and OpenCLIP. These models can classify waste without direct exposure to labeled examples by leveraging textual prompts. We apply this approach to the TrashNet dataset, which consists of images of municipal solid waste organized into six distinct categories: cardboard, glass, metal, paper, plastic, and trash. Our experimental results yield an average classification accuracy of 76.30% with Open Clip ViT-L/14-336 model, demonstrating the feasibility of zero-shot learning for waste classification while highlighting challenges in prompt sensitivity and class imbalance. Despite lower accuracy than CNN- and ViT-based classification models, zero-shot learning offers scalability and adaptability by enabling the classification of novel waste categories without retraining. This study underscores the potential of zero-shot learning in automated recycling systems, paving the way for more efficient, scalable, and annotation-free waste classification methodologies. Full article

The increase in garbage generated in modern societies demands the implementation of a more sustainable model as well as new methods for efficient waste management. This article describes the development and implementation of a prototype of a smart bin that automatically sorts waste using a multi-agent system and blockchain integration. The proposed system has sensors that identify the type of waste (organic, plastic, paper, etc.) and uses collaborative intelligent agents to make instant sorting decisions. Blockchain has been implemented as a technology for the immutable and transparent control of waste registration, favoring traceability during the classification process, providing sustainability to the process, and making the audit of data in smart urban environments transparent. For the computer vision algorithm, three versions of YOLO (YOLOv8, YOLOv11, and YOLOv12) were used and evaluated with respect to their performance in automatic detection and classification of waste. The YOLOv12 version was selected due to its overall performance, which is superior to others with mAP@50 values of 86.2%, an overall accuracy of 84.6%, and an average F1 score of 80.1%. Latency was kept below 9 ms per image with YOLOv12, ensuring smooth and lag-free processing, even for utilitarian embedded systems. This allows for efficient deployment in near-real-time applications where speed and immediate response are crucial. These results confirm the viability of the system in both accuracy and computational efficiency. This work provides an innovative solution in the field of ambient intelligence, characterized by low equipment cost and high scalability, laying the foundations for the development of smart waste management infrastructures in sustainable cities. Full article

The reliance on deep learning models for sensor-based material classification amplifies the demand for labeled training data. However, acquiring large-scale, annotated spectral data for applications such as near-infrared (NIR) reflectance spectroscopy in plastic sorting remains a significant challenge due to high acquisition costs and environmental variability. This paper investigates the potential of large language models (LLMs) in synthetic spectral data generation. Specifically, it examines whether LLMs have acquired sufficient implicit knowledge to assist in generating spectral data and introduce meaningful variations that enhance model performance when used for data augmentation. Classification accuracy is reported exclusively as a proxy for structural plausibility of the augmented spectra; maximizing augmentation performance itself is not the study’s goal. From as little as one empirical mean spectrum per class, LLM-guided simulation produced data that enabled up to 86% accuracy, evidence that the generated variation preserves class-distinguishing information. While the approach performs best for spectral distinct polymers, overlapping classes remain challenging. Additionally, the transfer of optimized augmentation parameters to unseen classes indicates potential for generalization across material types. While plastic sorting serves as a case study, the methodology may be applicable to other domains such as agriculture or food quality assessment, where spectral data are limited. The study outlines a novel path toward scalable, AI-supported data augmentation in spectroscopy-based classification systems. Full article

To ensure the green, safe, and efficient extraction of mineral resources and promote sustainability, the stability of mined-out areas has become a critical factor affecting safe production and ecological restoration in underground metal mines. The instability of underground goafs poses a significant threat to mine safety, especially when irregular excavation patterns interact with high ground stress, exacerbating instability risks. Most existing studies lack a systematic and multidisciplinary integrated framework for comprehensive evaluation and management. This paper proposes a trinity research system of “assessment–optimization–governance”, integrating theoretical analysis, three-dimensional fluid–solid coupling numerical simulation, and a filling sequence optimization method based on genetic algorithms. An analysis of data measured from 243 pillars and 49 goafs indicates that approximately 20–30% of the pillars have a factor of safety (FoS) below 1.0, signaling immediate instability risks; additionally, 58% do not meet the threshold for long-term stability (FoS ≥ 1.5). Statistical and spatial analyses highlight that pillar width-to-height ratio (W/H) and cross-sectional area significantly influence stability; when W/H exceeds 1.5, FoS typically surpasses 2.0. Numerical simulations reveal pore water pressures of 1.4–1.8 MPa in deeper goafs, substantially reducing effective stress and accelerating plastic zone expansion. Stability classification categorizes the 49 goafs into 7 “poor”, 37 “moderate”, and 5 “good” zones. A genetic algorithm-optimized filling sequence prioritizes high-risk area remediation, reducing maximum principal stress by 60.96% and pore pressure by 28.6%. Cemented waste rock filling applied in high-risk areas, complemented by general waste rock filling in moderate-risk areas, significantly enhances overall stability. This integrated method provides a scientific foundation for stability assessment and dynamic remediation planning under complex hydrogeological conditions, offering a risk-informed and scenario-specific application of existing tools that improves engineering applicability. Full article

Plastic waste and pollution is growing rapidly worldwide and most plastics end up in landfill or are incinerated because high-quality recycling is not possible. Plastic-type identification with a low-cost, handheld spectral approach could help in parts of the world where high-end spectral imaging systems on conveyor belts cannot be implemented. Here, we investigate how two fundamentally different handheld infrared spectral devices can identify plastic types by benchmarking the same analysis against a high-resolution bench-top spectral approach. We used the handheld Plastic Scanner, which measures a discrete infrared spectrum using LED illumination at different wavelengths, and the SpectraPod, which has an integrated photonics chip which has varying responsivity in different channels in the near-infrared. We employ machine learning using SVM, XGBoost, Random Forest and Gaussian Naïve Bayes models on a full dataset of plastic samples of PET, HDPE, PVC, LDPE, PP and PS, with samples of varying shape, color and opacity, as measured with three different experimental approaches. The high-resolution spectral approach can obtain an accuracy (mean ± standard deviation) of (0.97 ± 0.01), whereas we obtain (0.93 ± 0.01) for the SpectraPod and (0.70 ± 0.03) for the Plastic Scanner. Differences of reflectance at subsequent wavelengths prove to be the most important features in the plastic-type classification model when using high-resolution spectroscopy, which is not possible with the other two devices. Lower accuracy for the handheld devices is caused by their limitations, as the spectral range of both devices is limited—up to 1600 nm for the SpectraPod, while the Plastic Scanner has limited sensitivity to reflectance at wavelengths of 1100 and 1350 nm, where certain plastic types show characteristic absorbance bands. We suggest that combining selective sensitivity channels (as in the SpectraPod) and illuminating the sample with varying LEDs (as with the Plastic Scanner) could increase the accuracy in plastic-type identification with a handheld device. Full article

Hyperspectral imaging (HSI) is an advanced imaging technique that captures detailed spectral information across multiple fields. This review explores its applications in counterfeit detection, remote sensing, agriculture, medical imaging, cancer detection, environmental monitoring, mining, mineralogy, and food processing, specifically highlighting significant achievements from the past five years, providing a timely update across several fields. It also presents a cross-disciplinary classification framework to systematically categorize applications in medical, agriculture, environment, and industry. In counterfeit detection, HSI identified fake currency with high accuracy in the 400–500 nm range and achieved a 99.03% F1-score for counterfeit alcohol detection. Remote sensing applications include hyperspectral satellites, which improve forest classification accuracy by 50%, and soil organic matter, with the prediction reaching R² = 0.6. In agriculture, the HSI-TransUNet model achieved 86.05% accuracy for crop classification, and disease detection reached 98.09% accuracy. Medical imaging benefits from HSI’s non-invasive diagnostics, distinguishing skin cancer with 87% sensitivity and 88% specificity. In cancer detection, colorectal cancer identification reached 86% sensitivity and 95% specificity. Environmental applications include PM2.5 pollution detection with 85.93% accuracy and marine plastic waste detection with 70–80% accuracy. In food processing, egg freshness prediction achieved R² = 91%, and pine nut classification reached 100% accuracy. Despite its advantages, HSI faces challenges like high costs and complex data processing. Advances in artificial intelligence and miniaturization are expected to improve accessibility and real-time applications. Future advancements are anticipated to concentrate on the integration of deep learning models for automated feature extraction and decision-making in hyperspectral imaging analysis. The development of lightweight, portable HSI devices will enable more on-site applications in agriculture, healthcare, and environmental monitoring. Moreover, real-time processing methods will enhance efficiency for field deployment. These improvements seek to enhance the accessibility, practicality, and efficacy of HSI in both industrial and clinical environments. Full article

The Clonostachys genus is a saprophytic soil microfungus (Ascomycota). It exhibits significant ecological adaptability and plays a crucial role in maintaining the balance of soil microorganisms. Species within this genus are natural antagonists of insects and nematodes, and they also combat phytopathogenic fungi through mycoparasitism. This process involves producing lytic enzymes and competing for space and nutrients. Clonostachys species are effective biocontrol agents in agriculture and have been utilized to manage pests affecting many high-value commercial crops, acting as a natural biopesticide. They inhabit plant tissues, boosting plant defenses and activating genes for water and nutrient uptake, enhancing plant performance. Additionally, they produce enzymes and bioactive metabolites with antimicrobial, antifungal, nematocidal, anticancer, and antioxidant properties. Clonostachys species can degrade plastic waste and remove hydrocarbons from crude oil-contaminated sites when functioning as endophytes, positioning Clonostachys as a promising candidate for reducing environmental pollution. There are still challenges and limitations, such as the continuous surveillance of the safety of Clonostachys species on plants, the establishment of commercial applications, formulation viability, and variability due to field conditions. These issues will have to be addressed. This review provides an overview of Clonostachys ecology, morphology, classification, and biotechnological applications, emphasizing its significance in various fields. Full article

We report the design, implementation and test of a Mid-Infrared spectrometer proof-of-concept that utilizes an uncooled micro-bolometer array, sensitive in the 3–14 µm spectral range, integrated in a conventional optical dispersive spectrometry setup. Such a spectrometer enables instantaneous measurements across this broad spectral range, comparable to that of a FTIR but with a more compact design and without moving parts. This makes it ideal for integration into portable, battery-powered devices such as handheld scanners. The Mid-IR range offers significant advantages over NIR-SWIR spectrometers, especially for organic compound analysis. A notable application for this instrument: plastic waste sorting—including black plastics—was tested with significant accuracy and effectiveness of plastic classification (on PP, PET and PE samples) with a very simple machine learning algorithm. Full article

The residential separate collection of waste is the first stage in waste recyclability for sustainable development. The paper focuses on designing and implementing a low-cost residential automatic waste sorting bin (RBin) for recycling, alleviating the user’s classification burden. Next, an analysis of two object identification and classification models was conducted to sort materials into the categories of cardboard, glass, plastic, and metal. A major challenge in sorting classification is distinguishing between glass and plastic due to their similar visual characteristics. The research assesses the performance of the Azure Custom Vision Service (ACVS) model, which achieves high accuracy on training data but underperforms in real-time applications, with an accuracy of 95.13%. In contrast, the second model, the Custom Waste Sorting Model (CWSM), demonstrates high accuracy (96.25%) during training and proves to be effective in real-time applications. The CWSM uses a two-tier approach, first identifying the object descriptively using the Google Vision API Service (GVAS) model, followed by classification through the CWSM, a predicate-based custom model. The CWSM employs the LbfgsMaximumEntropyMulti algorithm and a dataset of 1000 records for training, divided equally across the categories. This study proposes an innovative evaluation metric, the Weighted Classification Confidence Score (WCCS). The results show that the CWSM outperforms ACVS in real-world testing, achieving a real accuracy of 99.75% after applying the WCCS. The paper explores the importance of customized models over pre-implemented services when the model uses characteristics and not pixel-by-pixel examination. Full article

Environmental contamination is ubiquitous and even in the ocean, signs of contamination of different types (chemical, biological, or plastic) are detected in all kinds of environments. In this study, a sediment core was sampled at the bottom of the Blue Hole of the Maldives (Ari Atoll) to make a first characterization of the sediment in terms of its grain size and organic–inorganic matter composition and to assess the sediment contamination levels in terms of trace elements (by ICP-MS analysis) and the eventual presence of microplastics (by optical classification and microRaman analysis of items). High concentrations of Hg (a maximum value of 0.145 ppm at the bottom layer of the core), Cd (a maximum value of 0.65 ppm at the core surface layer), and As (9.4 ppm at the top of the core) were highlighted at different layers of the sediment core. Plastic polymers were not detected in the sediment core, but 51 fibers characterized by the presence of artificial dyes or additives were found in the core (a mean of 5.7 fibers for each slice). The results confirmed the sediment contamination of the Maldivian Blue Hole, supporting the hypothesis of contamination due to ineffective waste management within the archipelago and mass tourism affecting the atolls. Full article

Waste management is one of the key areas where circular models should be promoted, as it plays a crucial role in minimizing environmental impact and conserving resources. Effective material identification and classification are essential for optimizing recycling processes and selecting the appropriate production equipment. Proper sorting of materials enhances both the efficiency and sustainability of recycling systems. The proposed study explores the potential of using a cost-effective strategy based on hyperspectral imaging (HSI) to classify space waste products, an emerging challenge in waste management. Specifically, it investigates the use of HSI sensors operating in the near-infrared range to detect and identify materials for sorting and classification. Analyses are focused on textile and plastic materials. The results show promising potential for further research, suggesting that the HSI approach is capable of effectively identifying and classifying various categories of materials. The predicted images achieve exceptional sensitivity and specificity, ranging from 0.989 to 1.000 and 0.995 to 1.000, respectively. Using cost-effective, non-invasive HSI technology could offer a significant improvement over traditional methods of waste classification, particularly in the challenging context of space operations. The implications of this work identify how technology enables the development of circular models geared toward sustainable development hence proper classification and distinction of materials as they allow for better material recovery and end-of-life management, ultimately contributing to more efficient recycling, waste valorization, and sustainable development practices. Full article

The traditional plastic sorting process primarily relies on manual operations, which are inefficient, pose safety risks, and result in suboptimal separation efficiency for mixed waste plastics. Near–infrared (NIR) spectroscopy, with its rapid and non–destructive analytical capabilities, presents a promising alternative. However, the analysis of NIR spectra is often complicated by overlapping peaks and complex data patterns, limiting its direct applicability. This study establishes a comprehensive machine learning–based NIR spectroscopy model to distinguish polypropylene (PP) at different aging stages. A dataset of NIR spectra was collected from PP samples subjected to seven simulated aging stages, followed by the construction of a classification model to analyze these spectral variations. The aging of PP was confirmed using Fourier–transform infrared spectroscopy (FTIR). Mechanical property analysis, including tensile strength and elongation at break, revealed a gradual decline with prolonged aging. After 40 days of accelerated aging, the elongation at the break of PP dropped to approximately 30%, retaining only about one–sixth of its original mechanical performance. Furthermore, various spectral preprocessing methods were evaluated to identify the most effective technique. The combination of the second derivative method with a linear –SVC achieved a classification accuracy of 99% and a precision of 100%. This study demonstrates the feasibility of the accurate identification of PP at different aging stages, thereby enhancing the quality and efficiency of recycled plastics and promoting automated, precise, and sustainable recycling processes. Full article

Plastic waste has become a critical environmental issue, necessitating effective methods for detection and monitoring. This article presents a machine-learning-based methodology and embedded solution to detect plastic waste in the environment using an airborne hyperspectral sensor operating in the short-wave infrared (SWIR) band. Experimental data were obtained from drone flights in several case studies in natural and controlled environments. Data were preprocessed to simply equalize the spectra across the whole band and across different environmental conditions, and machine learning techniques were applied to detect plastics even in real-time. Several algorithms for spectrum calibration, feature selection, and classification were optimized and compared to obtain an optimal solution that has high-quality results under cross-validation. This way, deploying the system in different environments without requiring complicated manual adjustments or re-learning is possible. The results of this work prove the feasibility of the proposed plastic litter detection approach using high-definition aerial remote sensing, with high specificity to plastic polymers that are not obtained using visible and NIR data. Full article

Despite the significant recycling potential, a massive generation of plastic waste is observed year after year. One of the causes of this phenomenon is the issue of ineffective waste stream sorting, primarily arising from the uncertainty in the composition of the waste stream. The recycling process cannot be carried out without the proper separation of different types of plastics from the waste stream. Current solutions in the field of automated waste stream identification rely on small-scale datasets that insufficiently reflect real-world conditions. For this reason, the article proposes a real-time identification model based on a CNN (convolutional neural network) and a newly constructed, self-built dataset. The model was evaluated in two stages. The first stage was based on the separated validation dataset, and the second was based on the developed test bench, a replica of the real system. The model was evaluated under laboratory conditions, with a strong emphasis on maximally reflecting real-world conditions. Once included in the sensor fusion, the proposed approach will provide full information on the characteristics of the waste stream, which will ultimately enable the efficient separation of plastic from the mixed stream. Improving this process will significantly support the United Nations’ 2030 Agenda for Sustainable Development. Full article

Plastic pollution is becoming an increasingly serious threat to the natural environment. Macroplastics, primarily polyethylene films, pose significant ecological and economic risks, particularly in the agricultural sector. Effective monitoring of their presence is necessary to evaluate the effectiveness of mitigation measures. Conventional techniques for identifying environmental contaminants, based on field studies, are often time-consuming and limited in scope. In response to these challenges, a study was conducted with the primary aim of utilizing unmanned aerial vehicles (UAVs), multispectral cameras, and classification tools to monitor macroplastic pollution. The model object for the study was an industrial compost pile. The performance of four object-oriented classifiers—Random Forest, k-Nearest Neighbor (k-NN), Maximum Likelihood, and Minimum Distance—was evaluated to effectively identify waste contamination. The best results were achieved with the k-NN classifier, which recorded a Matthews Correlation Coefficient (MCC) of 0.641 and an accuracy (ACC) of 0.891. The applied classifier identified a total 37.35% of the studied compost pile’s surface as contamination of plastic. The results of the study show that UAV technology, combined with multispectral imaging, can serve as an effective and relatively cost-efficient tool for monitoring macroplastic pollution in the environment. Full article