Sensors最新文献

Human interaction recognition (HIR) between two people in videos is a critical field in computer vision and pattern recognition, aimed at identifying and understanding human interaction and actions for applications such as healthcare, surveillance, and human-computer interaction. Despite its significance, video-based HIR faces challenges in achieving satisfactory performance due to the complexity of human actions, variations in motion, different viewpoints, and environmental factors. In the study, we proposed a two-stream deep learning-based HIR system to address these challenges and improve the accuracy and reliability of HIR systems. In the process, two streams extract hierarchical features based on the skeleton and RGB information, respectively. In the first stream, we utilised YOLOv8-Pose for human pose extraction, then extracted features with three stacked LSM modules and enhanced them with a dense layer that is considered the final feature of the first stream. In the second stream, we utilised SAM on the input videos, and after filtering the Segment Anything Model (SAM) feature, we employed integrated LSTM and GRU to extract the long-range dependency feature and then enhanced them with a dense layer that was considered the final feature for the second stream module. Here, SAM was utilised for segmented mesh generation, and ImageNet was used for feature extraction from images or meshes, focusing on extracting relevant features from sequential image data. Moreover, we newly created a custom filter function to enhance computational efficiency and eliminate irrelevant keypoints and mesh components from the dataset. We concatenated the two stream features and produced the final feature that fed into the classification module. The extensive experiment with the two benchmark datasets of the proposed model achieved 96.56% and 96.16% accuracy, respectively. The high-performance accuracy of the proposed model proved its superiority.

Background: Domain adaptation (DA) techniques have emerged as a pivotal strategy in addressing the challenges of cross-subject classification. However, traditional DA methods are inherently limited by the assumption of a homogeneous space, requiring that the source and target domains share identical feature dimensions and label sets, which is often impractical in real-world applications. Therefore, effectively addressing the challenge of EEG classification under heterogeneous spaces has emerged as a crucial research topic.

Methods: We present a comprehensive framework that addresses the challenges of heterogeneous spaces by implementing a cross-domain class alignment strategy. We innovatively construct a cross-encoder to effectively capture the intricate dependencies between data across domains. We also introduce a tailored class discriminator accompanied by a corresponding loss function. By optimizing the loss function, we facilitate the aggregation of features with corresponding classes between the source and target domains, while ensuring that features from non-corresponding classes are dispersed.

Results: Extensive experiments were conducted on two publicly available EEG datasets. Compared to advanced methods that combine label alignment with transfer learning, our method demonstrated superior performance across five heterogeneous space scenarios. Notably, in four heterogeneous label space scenarios, our method outperformed the advanced methods by an average of 7.8%. Moreover, in complex scenarios involving both heterogeneous label spaces and heterogeneous feature spaces, our method outperformed the state-of-the-art methods by an average of 4.1%.

Conclusions: This paper presents an efficient model for cross-subject EEG classification under heterogeneous spaces, which significantly addresses the challenges of EEG classification within heterogeneous spaces, thereby opening up new perspectives and avenues for research in related fields.

Iris is one of the most widely used biometric modalities because of its uniqueness, high matching performance, and inherently secure nature. Iris segmentation is an essential preliminary step for iris-based biometric authentication. The authentication accuracy is directly connected with the iris segmentation accuracy. In the last few years, deep-learning-based iris segmentation methodologies have increasingly been adopted because of their ability to handle challenging segmentation tasks and their advantages over traditional segmentation techniques. However, the biggest challenge to the biometric community is the scarcity of open-source resources for adoption for application and reproducibility. This review provides a comprehensive examination of available open-source iris segmentation resources, including datasets, algorithms, and tools. In the process, we designed three U-Net and U-Net++ architecture-influenced segmentation algorithms as standard benchmarks, trained them on a large composite dataset (>45K samples), and created 1K manually segmented ground truth masks. Overall, eleven state-of-the-art algorithms were benchmarked against five datasets encompassing multiple sensors, environmental conditions, demography, and illumination. This assessment highlights the strengths, limitations, and practical implications of each method and identifies gaps that future studies should address to improve segmentation accuracy and robustness. To foster future research, all resources developed during this work would be made publicly available.

To monitor health risks associated with vaping, we introduce a multi-spectral optical sensor powered by machine learning for real-time characterization of electronic cigarette aerosols. The sensor can accurately measure the mass of particulate matter (PM) in specific particle size channels, providing essential information for estimating lung deposition of vaping aerosols. For the sensor's input, wavelength-specific optical attenuation signals are acquired for three separate wavelengths in the ultraviolet, red, and near-infrared range, and the inhalation pressure is collected from a pressure sensor. The sensor's outputs are PM mass in three size bins, specified as 100-300 nm, 300-600 nm, and 600-1000 nm. Reference measurements of electronic cigarette aerosols, obtained using a custom vaping machine and a scanning mobility particle sizer, provided the ground truth for size-binned PM mass. A lightweight two-layer feedforward neural network was trained using datasets acquired from a wide range of puffing conditions. The performance of the neural network was tested using unseen data collected using new combinations of puffing conditions. The model-predicted values matched closely with the ground truth, and the accuracy reached 81-87% for PM mass in three size bins. Given the sensor's straightforward optical configuration and the direct collection of signals from undiluted vaping aerosols, the achieved accuracy is notably significant and sufficiently reliable for point-of-interest sensing of vaping aerosols. To the best of our knowledge, this work represents the first instance where machine learning has been applied to directly characterize high-concentration undiluted electronic cigarette aerosols. Our sensor holds great promise in tracking electronic cigarette users' puff topography with quantification of size-binned PM mass, to support long-term personalized health and wellness.

This study presents an advanced integration of Multi-modal Raman Light Sheet Microscopy with zero-shot learning-based computational methods to significantly enhance the resolution and analysis of complex three-dimensional biological structures, such as 3D cell cultures and spheroids. The Multi-modal Raman Light Sheet Microscopy system incorporates Rayleigh scattering, Raman scattering, and fluorescence detection, enabling comprehensive, marker-free imaging of cellular architecture. These diverse modalities offer detailed spatial and molecular insights into cellular organization and interactions, critical for applications in biomedical research, drug discovery, and histological studies. To improve image quality without altering or introducing new biological information, we apply Zero-Shot Deconvolution Networks (ZS-DeconvNet), a deep-learning-based method that enhances resolution in an unsupervised manner. ZS-DeconvNet significantly refines image clarity and sharpness across multiple microscopy modalities without requiring large, labeled datasets, or introducing artifacts. By combining the strengths of multi-modal light sheet microscopy and ZS-DeconvNet, we achieve improved visualization of subcellular structures, offering clearer and more detailed representations of existing data. This approach holds significant potential for advancing high-resolution imaging in biomedical research and other related fields.

Eucalyptus is a widely planted species in plantation forests because of its outstanding characteristics, such as fast growth rate and high adaptability. Accurate and rapid prediction of Eucalyptus biomass is important for plantation forest management and the prediction of carbon stock in terrestrial ecosystems. In this study, the performance of predictive biomass regression equations and machine learning algorithms, including multivariate linear stepwise regression (MLSR), support vector machine regression (SVR), and k-nearest neighbor (KNN) for constructing a predictive forest AGB model was analyzed and compared at individual tree and stand scales based on forest parameters extracted by Unmanned Aerial Vehicle-Light Detection and Ranging (UAV LiDAR) and variables screened by variable projection importance analysis to select the best prediction method. The results of the study concluded that the prediction model accuracy of the natural transformed regression equations (R² = 0.873, RMSE = 0.312 t/ha, RRMSE = 0.0091) outperformed that of the machine learning algorithms at the individual tree scale. Among the machine learning models, the SVR prediction model accuracy was the best (R² = 0.868, RMSE = 7.932 t/ha, RRMSE = 0.231). In this study, UAV-LiDAR-based data had great potential in predicting the AGB of Eucalyptus trees, and the tree height parameter had the strongest correlation with AGB. In summary, the combination of UAV LiDAR data and machine learning algorithms to construct a predictive forest AGB model has high accuracy and provides a solution for carbon stock assessment and forest ecosystem assessment.

Currently, analyzing pharmaceuticals and biomarkers is crucial for ensuring medication safety and protecting life and health, and there is an urgent need to develop new and efficient analytical techniques in view of the limitations of traditional analytical methods. Molecularly imprinted ratiometric fluorescent (MI-RFL) sensors have received increasing attention in the field of analytical detection due to their high selectivity, sensitivity and anti-interference ability, short response time, and visualization. This review summarizes the recent advances of MI-RFL sensors in the field of pharmaceuticals and biomarkers detection. Firstly, the fluorescence sources and working mechanisms of MI-RFL sensors are briefly introduced. On this basis, new techniques and strategies for preparing molecularly imprinted polymers, such as dummy template imprinting, nanoimprinting, multi-template imprinting, and stimulus-responsive imprinting strategies, are presented. Then, dual- and triple-emission types of fluorescent sensors are introduced. Subsequently, specific applications of MI-RFL sensors in pharmaceutical analysis and biomarkers detection are highlighted. In addition, innovative applications of MI-RFL sensors in point-of-care testing are discussed in-depth. Finally, the challenges of MI-RFL sensors for analysis of pharmaceuticals and biomarkers are proposed, and the research outlook and development trends of MI-RFL sensors are prospected.

Aerial images have distinct characteristics, such as varying target scales, complex backgrounds, severe occlusion, small targets, and dense distribution. As a result, object detection in aerial images faces challenges like difficulty in extracting small target information and poor integration of spatial and semantic data. Moreover, existing object detection algorithms have a large number of parameters, posing a challenge for deployment on drones with limited hardware resources. We propose an efficient small-object YOLO detection model (ESOD-YOLO) based on YOLOv8n for Unmanned Aerial Vehicle (UAV) object detection. Firstly, we propose that the Reparameterized Multi-scale Inverted Blocks (RepNIBMS) module is implemented to replace the C2f module of the Yolov8n backbone extraction network to enhance the information extraction capability of small objects. Secondly, a cross-level multi-scale feature fusion structure, wave feature pyramid network (WFPN), is designed to enhance the model's capacity to integrate spatial and semantic information. Meanwhile, a small-object detection head is incorporated to augment the model's ability to identify small objects. Finally, a tri-focal loss function is proposed to address the issue of imbalanced samples in aerial images in a straightforward and effective manner. In the VisDrone2019 test set, when the input size is uniformly 640 × 640 pixels, the parameters of ESOD-YOLO are 4.46 M, and the average mean accuracy of detection reaches 29.3%, which is 3.6% higher than the baseline method YOLOv8n. Compared with other detection methods, it also achieves higher detection accuracy with lower parameters.

Dependency between the conventional imbalance diagnostic feature and the shaft rotational speed makes imbalance diagnosis challenging for variable-speed machines. This paper focuses on an investigation of this dependency and on a proposal for a novel imbalance diagnostic feature and a novel simplified version for this feature, which are independent of shaft rotational speed. An equivalent mass-spring-damper system is investigated to find a closed-form expression describing this dependency. By normalizing the conventional imbalance diagnostic feature by the obtained dependency, a diagnostic feature is proposed. By conducting comprehensive experimental trials with a wind turbine with a permissible imbalance, it is justified that the proposed simplified version of imbalance diagnostic feature is speed-invariant.

Digital multi-beam synthesis technology is generally used in the on-orbit satellite-based Automatic Dependent Surveillance-Broadcast (ADS-B) system. However, the probability of successfully detecting aircraft with uneven surface distribution is low. An adaptive digital beamforming method is proposed to improve the efficiency of aircraft detection probability. The current method has the problem of long operation time and is not suitable for on-orbit operation. Therefore, this paper proposes an adaptive beamforming method for the ADS-B system based on a fully connected neural network (FCNN). The simulation results show that the calculation time of this method is about 2.6 s when more than 15,000 sets of data are inputted, which is 15-80% better than the existing methods. Its detection success probability is 10% higher than those of existing methods, and it has better robustness against large amounts of data.