Spatiotemporal Graph Convolutional Network for Riverine Microplastic Migration Pathway Identification and Pollution Source Tracing

Microplastic (MP) pollution is an emerging environmental issue. While it is evident that human activities are the primary source of MP pollution, the relationship between land use and MP pollution in rivers requires further study. Using data from 26 MP monitoring sites in the Chongqing section of the Yangtze River, we analyzed MP data along with land use and construction data. We improved the model for the Land Use Intensity Composite Index (LUI) to obtain correlations between land use and MP pollution. We found: 1) The concentration of microplastics in surface water (MPsw) in the Chongqing section of the Yangtze River gradually declined from upstream (central urban section of Chongqing) to downstream (northeastern section of Chongqing). 2) From 2016 to 2020, MPsw in the Chongqing section of the Yangtze River decreased by about 7.5-fold. 3) MPsw in the Chongqing section of the Yangtze River was positively correlated with the amount of surrounding urban and garden land. When the buffer radius was 1 km, the correlation coefficient was 0.53 (p < 0.05). With increasing buffer radius, the correlation between land use and gradually weakened. 4) The LUI was also strongly correlated with MPsw. The correlation was strongest when the buffer radius was 1 km, with a correlation coefficient of 0.59 (p < 0.05). At all buffer scales, microplastics in sediments (MPss) was positively correlated with village land and arable land . Unlike MPsw, as the buffer radius increased, the strength of the correlations between land use types and MPss gradually increased. The LUI was strongly correlated with MPsw . As the buffer radius increases, the correlation between the two gradually weakens. These results provide information useful for remediation and reduction of MP in river systems.

Microplastic contamination in urban aquatic environments: Occurrence characteristics in urban streams and stormwater runoff from urban surfaces

The problems are associated with microplastic (MP) pollution of global concern. However, little is known about the pollution characteristics and sources of MPs in urban green-belt soils. Therefore, this study investigated MP pollution in 11 sampling sites (22 green belts) in Shihezi City. The results showed that the abundance of MPs (0.02-5.00 mm) ranged from 287 ± 100 items/kg dw to 3227 ± 155 items/kg dw (mean + SD). Fibers (69.9%) accounted for the majority of MPs, and the MPs were mainly black (36.7%) and 0.02-0.5 mm (64.8%). The main types of MPs were polystyrene (PS) and polyethylene (PE). Compared with agricultural soil, the color and composition of green-belt soil MPs are diverse, which means that the source of green-belt soil MPs is more diverse. In different types of green-belt soil, MP pollution of industrial green land is more serious. Through cluster analysis and spatial distribution, fragments and fibers were found to have similar sources, mainly originating from food and textile industrial activities. This study provides important information for revealing MP pollutions in urban green-belt soils.

In order to provide intelligent and efficient healthcare services in the Internet of Medical Things (IoMT), human action recognition (HAR) can play a crucial role. As a result of their stringent requirements, such as high computational complexity and memory efficiency, classical HAR techniques are not applicable to modern and intelligent healthcare services, e.g., IoMT. To address these issues, we present in this paper a novel HAR technique for healthcare services in IoMT. This model, referred to as the spatio-temporal graph convolutional network (STGCN), primarily aims at skeleton-based human–machine interfaces. By independently extracting spatial and temporal features, STGCN significantly reduces information loss. Spatio-temporal information is extracted independently of the exact spatial and temporal point, ensuring the extraction of useful features for HAR. Using only joint data and fewer parameters, we demonstrate that our proposed STGCN achieved 92.2% accuracy on the skeleton dataset. Unlike multi-channel methods, which use a combination of joint and bone data and have a large number of parameters, multi-channel methods use both joint and bone data. As a result, STGCN offers a good balance between accuracy, memory consumption, and processing time, making it suitable for detecting medical conditions.

This study proposes a vessel position prediction method using attention spatiotemporal graph convolutional networks, which addresses the issue of low prediction accuracy due to less consideration of inter-feature dependencies in current vessel trajectory prediction methods. First, the method cleans the vessel trajectory data and uses the Time-ratio trajectory compression algorithm to compress the trajectory data, avoiding data redundancy and providing feature points for vessel trajectories. Second, the Spectral Temporal Graph Neural Network (StemGNN) extracts the correlation matrix that describes the relationship between multiple variables as a priori matrix input to the prediction model. Then the vessel trajectory prediction model is constructed, and the attention mechanism is added to the spatial and temporal dimensions of the trajectory data based on the spatio-temporal graph convolutional network at the same time as the above operations are performed on different time scales. Finally, the features extracted from different time scales are fused through the full connectivity layer to predict the future trajectories. Experimental results show that this method achieves higher accuracy and more stable prediction results in trajectory prediction. The attention-based spatio-temporal graph convolutional networks effectively capture the spatio-temporal correlations of the main features in vessel trajectories, and the spatio-temporal attention mechanism and graph convolution have certain interpretability for the prediction results.

Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition. To achieve effective analysis, spatio-temporal graph convolutional networks (ST-GCN) leverage the powerful learning ability to achieve great empirical successes; however, those methods need a huge amount of high-quality training data and lack theoretical interpretation. To address this issue, the spatio-temporal graph scattering transform (ST-GST) was proposed to put forth a theoretically interpretable framework; however, the empirical performance of this approach is constrained by the fully mathematical design. To benefit from both sides, this work proposes a novel complementary mechanism to organically combine the spatio-temporal graph scattering transform and neural networks, resulting in the proposed spatio-temporal graph complementary scattering networks (ST-GCSN). The essence is to leverage the mathematically designed graph wavelets with pruning techniques to cover major information and use trainable networks to capture complementary information. The empirical experiments on hand pose action recognition show that the proposed ST-GCSN outperforms both ST-GCN and ST-GST.

Tissue-specific microplastic burden in cetacean non-digestive organs.

Microplastic pollution has become a global concern, with potential negative impacts on various ecosystems and wildlife species. Among these species, ducks (Anas platyrhynchos) are particularly vulnerable due to their feeding habits and proximity to aquatic environments contaminated with microplastics. The current study was designed to monitor microplastic (MP) pollutants in the freshwater ecosystem of the Panjkora River, Lower Dir, Pakistan. A total of twenty (20) duck samples were brought up for four months and 13 days on the banks of the river, with no food intake outside the river. When they reached an average weight of 2.41 ± 0.53 kg, all samples were sacrificed, dissected, and transported in an ice box to the laboratory for further analysis. After sample preparation, such as digestion with 10% potassium hydroxide (KOH), density separation, filtration, and identification, the MP content was counted. A total of 2033 MP particles were recovered from 20 ducks with a mean value of 44.6 ± 15.8 MPs/crop and 57.05 ± 18.7 MPs/gizzard. MPs detected in surface water were 31.2 ± 15.5 MPs/L. The major shape types of MPs recovered were fragments in crop (67%) and gizzard (58%) samples and fibers in surface water (56%). Other types of particles recovered were fibers, sheets, and foams. The majority of these detected MP particles were in the size range of 300-500 µm (63%) in crops, and 50-150 µm (55%) in gizzards, while in water samples the most detected particles were in the range of 150-300 µm (61%). Chemical characterization by FTIR found six types of polymers. Low-density polyethylene (LDPE) had the greatest polymer detection rate (39.2%), followed by polyvinyl chloride (PVC) (28.3%), high-density polyethylene (HDPE) (22.7%), polystyrene (6.6%), co-polymerized polypropylene (2.5%), and polypropylene homopolymer (0.7%). This study investigated the presence of microplastics in the crops and gizzards of ducks, as well as in river surface water. The results revealed the significant and pervasive occurrence of microplastics in both the avian digestive systems and the surrounding water environment. These findings highlight the potential threat of microplastic pollution to wildlife and ecosystems, emphasizing the need for further research and effective mitigation strategies to address this pressing environmental concern.

The reason why China’s table tennis can continue to this day is because it is an important heritage sports event in the country. In order to ensure the high-level performance of the Chinese table tennis team in the game, the identification and detection of its sports characteristics is a very meaningful work. With the development of computer technology, the use of multimedia intelligence technology to conduct research on competitive tactics has become a general consensus in the sports world. This paper explores the recognition and detection technology of the strength of table tennis hitting movements from the perspective of biomechanics, aiming to provide scientific basis and technical support for improving the performance of athletes. Based on the principles of biomechanics and combined with multimedia intelligent algorithms, this study developed a spatiotemporal graph convolutional network (STGCN) and a motion detection method based on Kinect technology to identify and quantify the hitting strength of table tennis players. The experimental results of this paper show that in the recognition of different types of movements based on the STGCN method, the correct recognition rate of 100 groups of movement strength is 84%, and the correct recognition rate of 500 groups of movement strength is 91.6%; in the recognition of different types of movement strength based on Kinect, the correct recognition rate of 100 groups of movement strength is 97%, and the correct recognition rate of 500 groups of movement strength is 99.6%; it can be seen that no matter how many groups of hitting movements are made, the correct recognition rate of strength based on Kinect is higher than that of STGCN.

IntroductionAccurately recognizing and understanding human motion actions presents a key challenge in the development of intelligent sports robots. Traditional methods often encounter significant drawbacks, such as high computational resource requirements and suboptimal real-time performance. To address these limitations, this study proposes a novel approach called Sports-ACtrans Net.MethodsIn this approach, the Swin Transformer processes visual data to extract spatial features, while the Spatio-Temporal Graph Convolutional Network (ST-GCN) models human motion as graphs to handle skeleton data. By combining these outputs, a comprehensive representation of motion actions is created. Reinforcement learning is employed to optimize the action recognition process, framing it as a sequential decision-making problem. Deep Q-learning is utilized to learn the optimal policy, thereby enhancing the robot's ability to accurately recognize and engage in motion.Results and discussionExperiments demonstrate significant improvements over state-of-the-art methods. This research advances the fields of neural computation, computer vision, and neuroscience, aiding in the development of intelligent robotic systems capable of understanding and participating in sports activities.

Spatio-temporal Graph Convolutional Networks (ST-GCNs) have shown great performance in the context of skeleton-based action recognition. Nevertheless, ST-GCNs use raw skeleton data as vertex features. Such features have low dimensionality and might not be optimal for action discrimination. Moreover, a single layer of temporal convolution is used to model short-term temporal dependencies but can be insufficient for capturing both long-term. In this paper, we extend the Spatio-Temporal Graph Convolutional Network for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D 60, NTU RGB-D 120 and Kinetics datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.

Spatio-temporal Graph Convolutional Networks (ST-GCNs) have shown great performance in the context of skeleton-based action recognition. Nevertheless, ST-GCNs use raw skeleton data as vertex features. Such features have low dimensionality and might not be optimal for action discrimination. Moreover, a single layer of temporal convolution is used to model short-term temporal dependencies but can be insufficient for capturing both long-term. In this paper, we extend the Spatio-Temporal Graph Convolutional Network for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D 60, NTU RGB-D 120 and Kinetics datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.

Microplastics are the newly identified pollutant of this century, yet they are already detected everywhere worldwide. Microplastic pollution in global marine environments has been intensively reported. Evidence of microplastic pollution is emerging in other environments, including land, freshwater, atmosphere, and organisms. Public concerns were also raised about microplastic pollution around them. From terrestrial environments, through freshwater environments, finally to marine environments, is a major transportation route of microplastic pollution. Human activities are the fundamental source of microplastic pollution. Cities, with the highest population density on this planet, are important sources of microplastic pollutants. This chapter focuses on urban freshwater environments, the first receptor, and major transporter of urban microplastics. By reviewing microplastic pollution in global urban freshwater catchments, urban microplastic pollution characteristics were clarified, and the key information to prevent urban microplastic discharge was sought.

This study introduces the MSTA-GNet (Multi-Scale Spatiotemporal Attention Graph Network), a novel deep learning model which integrates spatiotemporal self-attention mechanisms to model heterogeneous dependencies in traffic networks. The primary objective of the study is to improve existing traffic flow prediction models to address the inadequacies of traditional models in complex big data environments. Key innovations of the MSTA-GNet model include positional encoding and global and local self-attention mechanisms to capture long-term and short-term dependencies. Using the PeMS (Performance Measurement System) dataset, the study conducted performance comparison experiments among various deep learning models, including LSTM (Long Short-Term Memory), GCN (Graph Convolutional Network), DCRNN (Diffusion Convolutional Recurrent Neural Network), STGCN (Spatiotemporal Graph Convolutional Network), STMetaNet (Spatiotemporal Meta Network), and MSTA-GNet. The results showed that MSTA-GNet significantly outperformed other models with improvements of 13.4%, 11.8%, and 9.7% in Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics, respectively. Ablation studies further validated the significance of attention mechanisms, feature extraction, convolutional layers, and graph networks, confirming the effectiveness and practical application of MSTA-GNet in traffic flow prediction. This research provides important insights for AI-based congestion management, support for low-carbon traffic networks, and optimization of local traffic operations, demonstrating its significant practical value in intelligent transportation systems.

Microplastic pollution from protective measures in urban construction should not be overlooked: A case study in Changzhou, China.