Source analysis and health risk assessment of polycyclic aromatic hydrocarbon (PAHs) in total suspended particulate matter (TSP) from Bengbu, China.

The polycyclic aromatic hydrocarbon (PAH) concentrations in total suspended particulate matter (TSP) samples collected from October, 2021 to September, 2022 were analyzed to clarify the pollution characteristics and sources of 16 PAHs in the atmospheric TSP in Bengbu City. The ρ(PAHs) concentrations ranged from 1.71 to 43.85 ng/m3 and higher concentrations were detected in winter, followed by spring, autumn, and summer. The positive matrix factorization analysis revealed that, in spring and summer, PAH pollution was caused mainly by industrial emissions, gasoline and diesel fuel combustion, whereas in autumn and winter, it was coal, biomass and natural gas combustion. The cluster and potential source factor analyses showed that long-range transport was a significant factor. During spring, autumn, and winter, the northern and northwestern regions had a significant impact, whereas the coastal area south of Bengbu had the greatest influence in summer. The health risk assessment revealed that the annual total carcinogenic equivalent concentration values for PAHs varied from 0.0159 to 7.437 ng/m3, which was classified as moderate. Furthermore, the annual incremental lifetime cancer risk values ranged from 1.431 × 10-4 to 3.671 × 10-3 for adults and from 6.823 × 10-5 to 1.749 × 10-3 for children, which were higher than the standard.

Deep Temporal Model-Based Identity-Aware Hand Detection for Space Human-Robot Interaction.

Hand detection is a crucial technology for space human-robot interaction (SHRI), and the awareness of hand identities is particularly critical. However, most advanced works have three limitations: 1) the low detection accuracy of small-size objects; 2) insufficient temporal feature modeling between frames in videos; and 3) the inability of real-time detection. In the article, a temporal detector (called TA-RSSD) is proposed based on the SSD and spatiotemporal long short-term memory (ST-LSTM) for real-time detection in SHRI applications. Next, based on the online tubelet analysis, a real-time identity-awareness module is designed for multiple hand object identification. Several notable properties are described as follows: 1) the hybrid structure of the Resnet-101 and the SSD improves the detection accuracy of small objects; 2) three-level feature pyramidal structure retains rich semantic information without losing detailed information; 3) a group of the redesigned temporal attentional LSTM (TA-LSTM) is utilized for three-level feature map modeling, which effectively achieves background suppression and scale suppression; 4) low-level attention maps are used to eliminate in-class similarity between hand objects, which improves the accuracy of identity awareness; and 5) a novel association training scheme enhances the temporal coherence between frames. The proposed model is evaluated on the SHRI-VID dataset (collected according to the task requirements), the AU-AIR dataset, and the ImageNet-VID benchmark. Extensive ablation studies and comparisons on detection and identity-awareness capacities show the superiority of the proposed model. Finally, a set of actual testing is conducted on a space robot, and the results show that the proposed model achieves a real-time speed and high accuracy.

How to Represent Paintings: A Painting Classification Using Artistic Comments.

The goal of large-scale automatic paintings analysis is to classify and retrieve images using machine learning techniques. The traditional methods use computer vision techniques on paintings to enable computers to represent the art content. In this work, we propose using a graph convolutional network and artistic comments rather than the painting color to classify type, school, timeframe and author of the paintings by implementing natural language processing (NLP) techniques. First, we build a single artistic comment graph based on co-occurrence relations and document word relations and then train an art graph convolutional network (ArtGCN) on the entire corpus. The nodes, which include the words and documents in the topological graph are initialized using a one-hot representation; then, the embeddings are learned jointly for both words and documents, supervised by the known-class training labels of the paintings. Through extensive experiments on different classification tasks using different input sources, we demonstrate that the proposed methods achieve state-of-art performance. In addition, ArtGCN can learn word and painting embeddings, and we find that they have a major role in describing the labels and retrieval paintings, respectively.

Compare the performance of the models in art classification.

Because large numbers of artworks are preserved in museums and galleries, much work must be done to classify these works into genres, styles and artists. Recent technological advancements have enabled an increasing number of artworks to be digitized. Thus, it is necessary to teach computers to analyze (e.g., classify and annotate) art to assist people in performing such tasks. In this study, we tested 7 different models on 3 different datasets under the same experimental setup to compare their art classification performances when either using or not using transfer learning. The models were compared based on their abilities for classifying genres, styles and artists. Comparing the result with previous work shows that the model performance can be effectively improved by optimizing the model structure, and our results achieve state-of-the-art performance in all classification tasks with three datasets. In addition, we visualized the process of style and genre classification to help us understand the difficulties that computers have when tasked with classifying art. Finally, we used the trained models described above to perform similarity searches and obtained performance improvements.

Attribute-Driven Granular Model for EMG-Based Pinch and Fingertip Force Grand Recognition.

Fine multifunctional prosthetic hand manipulation requires precise control on the pinch-type and the corresponding force, and it is a challenge to decode both aspects from myoelectric signals. This paper proposes an attribute-driven granular model (AGrM) under a machine-learning scheme to solve this problem. The model utilizes the additionally captured attribute as the latent variable for a supervised granulation procedure. It was fulfilled for EMG-based pinch-type classification and the fingertip force grand prediction. In the experiments, 16 channels of surface electromyographic signals (i.e., main attribute) and continuous fingertip force (i.e., subattribute) were simultaneously collected while subjects performing eight types of hand pinches. The use of AGrM improved the pinch-type recognition accuracy to around 97.2% by 1.8% when constructing eight granules for each grasping type and received more than 90% force grand prediction accuracy at any granular level greater than six. Further, sensitivity analysis verified its robustness with respect to different channel combination and interferences. In comparison with other clustering-based granulation methods, AGrM achieved comparable pinch recognition accuracy but was of lowest computational cost and highest force grand prediction accuracy.

Simultaneous Prediction of Wrist/Hand Motion via Wearable Ultrasound Sensing.

The ability to predict wrist and hand motions simultaneously is essential for natural controls of hand protheses. In this paper, we propose a novel method that includes subclass discriminant analysis (SDA) and principal component analysis for the simultaneous prediction of wrist rotation (pronation/supination) and finger gestures using wearable ultrasound. We tested the method on eight finger gestures with concurrent wrist rotations. Results showed that SDA was able to achieve accurate classification of both finger gestures and wrist rotations under dynamic wrist rotations. When grouping the wrist rotations into three subclasses, about 99.2 ± 1.2% of finger gestures and 92.8 ± 1.4% of wrist rotations can be accurately classified. Moreover, we found that the first principal component (PC1) of the selected ultrasound features was linear to the wrist rotation angle regardless of finger gestures. We further used PC1 in an online tracking task for continuous wrist control and demonstrated that a wrist tracking precision ( R2 ) of 0.954 ± 0.012 and a finger gesture classification accuracy of 96.5 ± 1.7% can be simultaneously achieved, with only two minutes of user training. Our proposed simultaneous wrist/hand control scheme is training-efficient and robust, paving the way for musculature-driven artificial hand control and rehabilitation treatment.

Ultrasonography and electromyography based hand motion intention recognition for a trans-radial amputee: A case study.

Surface electromyography (sEMG) has dominated upper-limb prosthesis control for decades due to its simplicity and effectiveness [1-3]. However, the inherent variability of EMG signal hinders the flexible and accurate control of advanced multi-functional prosthesis. This study is an attempt to use ultrasonography (US) as an alternative for prosthetic hand control. A type of multi-sensory module, comprising a single-element ultrasound channel and one sEMG bipolar channel, is customised to ensure a fair comparison between these two modalities. Three machine-learning-oriented approaches were adopted to evaluate the performance in motion classification based on datasets captured from a trans-radial amputee. The experimental results demonstrated that the ultrasound outperformed the sEMG in random (98.9% vs 70.4%) and enhanced-trial-wise (74.10% vs 61.83%) cross-validation, but fell behind the sEMG in trial-wise (39.47% vs 58.04%) validation that is the closest comparison to a real life prosthetic control. This study preliminarily implies that 1) A-mode ultrasound signal can be more stable than the sEMG with minimum electrode shift, but more sensitive to external interference than the sEMG; and 2) to maintain high classification accuracy, US approach may require harsher electrode fixing mechanism or advanced on-line calibration approach.

Towards Zero Re-Training for Long-Term Hand Gesture Recognition via Ultrasound Sensing.

While myoelectric pattern recognition is a prevailing way for gesture recognition, the inherent nonstationarity of electromyography signals hinders its long-term application. This study aims to prove a hypothesis that morphological information of muscle contraction detected by ultrasound image is potentially suitable for long-term use. A set of ultrasound-based algorithms are proposed to realize robust hand gesture recognition over multiple days, with user training only at the first day. A markerless calibration algorithm is first presented to position the ultrasound probe during donning and doffing; an algorithm combining speeded-up robust features and bag-of-features model being immune to ultrasound probe shift and rotation is then introduced; a self-enhancing classification method is next adopted to update classification model automatically by incorporating useful knowledge from testing data; finally the performance of long-term hand gesture recognition with zero re-training is validated by a six-day experiment of six healthy subjects, whose outcomes strongly support the hypothesis with about 94% of gesture recognition accuracy for each testing day. This study confirms the feasibility of adoption of ultrasound sensing for long-term musculature related applications.

Ultrasound-Based Sensing Models for Finger Motion Classification.

Motions of the fingers are complex since hand grasping and manipulation are conducted by spatial and temporal coordination of forearm muscles and tendons. The dominant methods based on surface electromyography (sEMG) could not offer satisfactory solutions for finger motion classification due to its inherent nature of measuring the electrical activity of motor units at the skin's surface. In order to recognize morphological changes of forearm muscles for accurate hand motion prediction, ultrasound imaging is employed to investigate the feasibility of detecting mechanical deformation of deep muscle compartments in potential clinical applications. In this study, finger motion classification has been represented as subproblems: recognizing the discrete finger motions and predicting the continuous finger angles. Predefined 14 finger motions are presented in both sEMG signals and ultrasound images and captured simultaneously. Linear discriminant analysis classifier shows the ultrasound has better average accuracy (95.88%) than the sEMG (90.14%). On the other hand, the study of predicting the metacarpophalangeal (MCP) joint angle of each finger in nonperiod movements also confirms that classification method based on ultrasound achieves better results (average correlation 0.89 $\pm$ 0.07 and NRMSE 0.15 $\pm$ 0.05) than sEMG (0.81 $\pm$ 0.09 and 0.19 $\pm$ 0.05). The research outcomes evidently demonstrate that the ultrasound can be a feasible solution for muscle-driven machine interface, such as accurate finger motion control of prostheses and wearable robotic devices.

Towards Wearable A-Mode Ultrasound Sensing for Real-Time Finger Motion Recognition.

It is evident that surface electromyography (sEMG) based human-machine interfaces (HMI) have inherent difficulty in predicting dexterous musculoskeletal movements such as finger motions. This paper is an attempt to investigate a plausible alternative to sEMG, ultrasound-driven HMI, for dexterous motion recognition due to its characteristic of detecting morphological changes of deep muscles and tendons. A multi-channel A-mode ultrasound lightweight device is adopted to evaluate the performance of finger motion recognition; an experiment is designed for both widely acceptable offline and online algorithms with eight able-bodied subjects employed. The experiment result presents that the offline recognition accuracy is up to 98.83% ± 0.79%. The real-time motion completion rate is 95.4% ± 8.7% and online motion selection time is 0.243 ± 0.127 s. The outcomes confirm the feasibility of A-mode ultrasound based wearable HMI and its prosperous applications in prosthetic devices, virtual reality, and remote manipulation.

Interface Prostheses With Classifier-Feedback-Based User Training.

It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.