In this paper, we proposed an accurate and robust method for absolute pose estimation with UAV (unmanned aerial vehicle) using RANSAC (random sample consensus). Because the artificial 3D control points with high accuracy are time-consuming and the small point set may lead low measuring accuracy, we designed a customized UAV to efficiently obtain mass 3D points. A light source was mounted on the UAV and used as a 3D point. The position of the 3D point was given by RTK (real-time kinematic) mounted on the UAV, and the position of the corresponding 2D point was given by feature extraction. The 2D–3D point correspondences exhibited some outliers because of the failure of feature extraction, the error of RTK, and wrong matches. Hence, RANSAC was used to remove the outliers and obtain the coarse pose. Then, we proposed a method to refine the coarse pose, whose procedure was formulated as the optimization of a cost function about the reprojection error based on the error transferring model and gradient descent to refine it. Before that, normalization was given for all the valid 2D–3D point correspondences to improve the estimation accuracy. In addition, we manufactured a prototype of a UAV with RTK and light source to obtain mass 2D–3D point correspondences for real images. Lastly, we provided a thorough test using synthetic data and real images, compared with several state-of-the-art perspective-n-point solvers. Experimental results showed that, even with a high outlier ratio, our proposed method had better performance in terms of numerical stability, noise sensitivity, and computational speed. Full article

Deep learning techniques have brought substantial performance gains to remote sensing image classification. Among them, convolutional neural networks (CNN) can extract rich spatial and spectral features from hyperspectral images in a short-range region, whereas graph convolutional networks (GCN) can model middle- and long-range spatial relations (or structural features) between samples on their graph structure. These different features make it possible to classify remote sensing images finely. In addition, hyperspectral images and light detection and ranging (LiDAR) images can provide spatial-spectral information and elevation information of targets on the Earth’s surface, respectively. These multi-source remote sensing data can further improve classification accuracy in complex scenes. This paper proposes a classification method for HS and LiDAR data based on a dual-coupled CNN-GCN structure. The model can be divided into a coupled CNN and a coupled GCN. The former employs a weight-sharing mechanism to structurally fuse and simplify the dual CNN models and extracting the spatial features from HS and LiDAR data. The latter first concatenates the HS and LiDAR data to construct a uniform graph structure. Then, the dual GCN models perform structural fusion by sharing the graph structures and weight matrices of some layers to extract their structural information, respectively. Finally, the final hybrid features are fed into a standard classifier for the pixel-level classification task under a unified feature fusion module. Extensive experiments on two real-world hyperspectral and LiDAR data demonstrate the effectiveness and superiority of the proposed method compared to other state-of-the-art baseline methods, such as two-branch CNN and context CNN. In particular, the overall accuracy (99.11%) on Trento achieves the best classification performance reported so far. Full article

Force and effort are important components of a motor task that can impact rehabilitation effectiveness. However, few studies have evaluated the impact of these factors on cortical activation during gait. The purpose of the study was to investigate the relation between cortical activation and effort required during exoskeleton-mediated gait at different levels of physical assistance in healthy individuals. Twenty-four healthy participants walked 10 m with an exoskeleton that provided four levels of assistance: 100%, 50%, 0%, and 25% resistance. Functional near-infrared spectroscopy (fNIRS) was used to measure cerebral flow dynamics with a 20-channel (plus two reference channels) device that covered most cortical motor regions bilaterally. We measured changes in oxyhemoglobin (HbO₂) and deoxyhemoglobin (HbR). According to HbO₂ levels, cortical activation only differed slightly between the assisted conditions and rest. In contrast, bilateral and widespread cortical activation occurred during the two unassisted conditions (somatosensory, somatosensory association, primary motor, premotor, and supplementary motor cortices). A similar pattern was seen for HbR levels, with a smaller number of significant channels than for HbO₂. These results confirmed the hypothesis that there is a relation between cortical activation and level of effort during gait. This finding should help to optimize neurological rehabilitation strategies to drive neuroplasticity. Full article

This study introduces an alternative to the existing methods for measuring ocean currents based on a recently developed technology. The SailBuoy is an unmanned surface vehicle powered by wind and solar panels that can navigate autonomously to predefined waypoints and record velocity profiles using an integrated downward-looking acoustic Doppler current profiler (ADCP). Data collected on two validation campaigns show a satisfactory correlation between the SailBuoy current records and traditional observation techniques such as bottom-mounted and moored current profilers and moored single-point current meter. While the highest correlations were found in tidal signals, strong current, and calm weather conditions, low current speeds and varying high wave and wind conditions reduced correlation considerably. Filtering out some events with the high sea surface roughness associated with high wind and wave conditions may increase the SailBuoy ADCP listening quality and lead to better correlations. Not yet resolved is a systematic offset between the measurements obtained by the SailBuoy and the reference instruments of ±0.03 m/s. Possible reasons are discussed to be the differences between instruments (various products) as well as changes in background noise levels due to environmental conditions. Full article

With the increasingly widespread application of UAV intelligence, the need for autonomous navigation and positioning is becoming more and more important. To solve the problem that UAV cannot perform localization in complex scenes, a new multi-source fusion framework factor graph optimization algorithm is used for UAV localization state estimation in this paper, which is based on IMU/GNSS/VO multi-source sensors. Based on the factor graph model and the iSAM incremental inference algorithm, a multi-source fusion model of IMU/GNSS/VO is established, including the IMU pre-integration factor, IMU bias factor, GNSS factor, and VO factor. Mathematical simulations and validations on the EuRoC dataset show that, when the selected sliding window size is 30, the factor graph optimization (FGO) algorithm can not only meet the requirements of real time and accuracy at the same time, but it also achieves a plug-and-play function in the event of local sensor failures. Finally, compared with the traditional federated Kalman algorithm and the adaptive federated Kalman algorithm, the positioning accuracy of the FGO algorithm in this paper is improved by 1.5–2-fold, and can effectively improve autonomous navigation system robustness and flexibility in complex scenarios. Moreover, the multi-source fusion framework in this paper is a general algorithm framework that can satisfy other scenarios and other types of sensor combinations. Full article

Nitrites are widely used in the food industry, particularly for the preservation of meat products. Controlling the nitrate content in food is an important task to ensure people’s health is not at risk; therefore, the search for, and research of, new materials that will modify the electrodes in the electrochemical sensors that detect and control the nitrate content in food products is an urgent task. In this paper, we describe the electrochemical behavior of a glass carbon electrode (GCE), modified with a Fe(II) tetra-tert-butyl phthalocyanine film (FePc(tBu)₄/GCE), and decorated with gold nanoparticles (Au/FePc(tBu)₄/GCE); this electrode was deposited using gas-phase methods. The composition and morphology of such electrodes were examined using spectroscopy and electron microscopy methods, whereas the main electrochemical characteristics were determined using cyclic voltammetry (CV) and amperometry (CA) methods in the linear ranges of CV 0.25–2.5 mM, CA 2–120 μM in 0.1 M phosphate buffer (pH = 6.8). The results showed that the modification of bare GCEs, with a Au/FePc(tBu)₄ heterostructure, provided a high surface-to-volume ratio, thus ensuring its high sensitivity to nitrite ions of 0.46 μAμM⁻¹. The sensor based on the Au/FePc(tBu)₄/GCE has a low limit of nitrite detection at 0.35 μM, good repeatability, and stability. The interference study showed that the proposed Au/FePc(tBu)₄/GCE exhibited a selective response in the presence of interfering anions, and the analytical capability of the sensor was demonstrated by determining nitrite ions in real samples of meat products. Full article

In the era of big data, using big data to realize the online estimation of battery SOH has become possible. Traditional solutions based on theoretical models cannot take into account driving behavior and complicated environmental factors. In this paper, an approximate SOH degradation model based on real operating data and environmental temperature data of electric vehicles (EVs) collected with a big data platform is proposed. Firstly, the health indicators are extracted from the historical operating data, and the equivalent capacity at 25 °C is obtained based on the capacity–temperature empirical formula and the capacity offset. Then, the attenuation rate during each charging and discharging process is calculated by combining the operating data and the environmental temperature. Finally, the long short-term memory (LSTM) neural network is used to learn the degradation trend of the battery and predict the future decline trend. The test results show that the proposed method has better performance. Full article

To solve the problem of low accuracy and slow speed of drone detection in high-resolution images with fixed cameras, we propose a detection method combining background difference and lightweight network SAG-YOLOv5s. First, background difference is used to extract potential drone targets in high-resolution images, eliminating most of the background to reduce computational overhead. Secondly, the Ghost module and SimAM attention mechanism are introduced on the basis of YOLOv5s to reduce the total number of model parameters and improve feature extraction, and α-DIoU loss is used to replace the original DIoU loss to improve the accuracy of bounding box regression. Finally, to verify the effectiveness of our method, a high-resolution drone dataset is made based on the public data set. Experimental results show that the detection accuracy of the proposed method reaches 97.6%, 24.3 percentage points higher than that of YOLOv5s, and the detection speed in 4K video reaches 13.2 FPS, which meets the actual demand and is significantly better than similar algorithms. It achieves a good balance between detection accuracy and detection speed and provides a method benchmark for high-resolution drone detection under a fixed camera. Full article

In preparation for the battlefields of the future, using unmanned aerial vehicles (UAV) loaded with multisensors to track dynamic targets has become the research focus in recent years. According to the air combat tracking scenarios and traditional multisensor weighted fusion algorithms, this paper contains designs of a new data fusion method using a global Kalman filter and LSTM prediction measurement variance, which uses an adaptive truncation mechanism to determine the optimal weights. The method considers the temporal correlation of the measured data and introduces a detection mechanism for maneuvering of targets. Numerical simulation results show the accuracy of the algorithm can be improved about 66% by training 871 flight data. Based on a mature refitted civil wing UAV platform, the field experiments verified the data fusion method for tracking dynamic target is effective, stable, and has generalization ability. Full article

This article presents an atypical offline based LoRaWAN application for use in hospital settings, where the ability to maintain network connectivity during internet connection disruption is paramount. A prototype bed rail is demonstrated, providing advanced functionality compared to traditional bed rails. The manufactured prototype provides data to a nurses station reliably and operates under battery backup. The power consumption of the system under different transmission intervals was tested, allowing appropriate battery sizing for different applications to be specified accurately. It is expected that a single LoRaWAN gateway will be able to cover bed rails across an entire modern hospital, allowing minimal infrastructure cost to implement the device or application in a rapidly deployed field hospital. Full article

pH is an important parameter for water quality detection. This study proposed a novel calibration regression strategy based on a one-dimensional convolutional neural network (1D-CNN) for water pH detection using visible near-infrared (Vis-NIR) spectroscopy. Two groups of Vis-NIR spectral analysis experiments of water pH detection were employed to evaluate the performance of 1D-CNN. Two conventional multivariate regression calibration methods, including partial least squares (PLS) and least squares support vector machine (LS-SVM), were introduced for comparative analysis with 1D-CNN. The successive projections algorithm (SPA) was adopted to select the feature variables. In addition, the learning mechanism of 1D-CNN was interpreted through visual feature maps by convolutional layers. The results showed that the 1D-CNN models obtained the highest prediction accuracy based on full spectra for the two experiments. For the spectrophotometer experiment, the root mean square error of prediction (RMSEP) was 0.7925, and the determination coefficient of prediction ($R_p^2$) was 0.8515. For the grating spectrograph experiment, the RMSEP was 0.5128 and the $R_p^2$ was 0.9273. The convolutional layers could automatically preprocess the spectra and effectively extract the spectra features. Compared with the traditional regression methods, 1D-CNN does not need complex spectra pretreatment and variable selection. Therefore, 1D-CNN is a promising regression approach, with higher prediction accuracy and better modeling convenience for rapid water pH detection using Vis-NIR spectroscopy. Full article

The core of underwater acoustic recognition is to extract the spectral features of targets. The running speed and track of the targets usually result in a Doppler shift, which poses significant challenges for recognizing targets with different Doppler frequencies. This paper proposes deep learning with a channel attention mechanism approach for underwater acoustic recognition. It is based on three crucial designs. Feature structures can obtain high-dimensional underwater acoustic data. The feature extraction model is the most important. First, we develop a ResNet to extract the deep abstraction spectral features of the targets. Then, the channel attention mechanism is introduced in the camResNet to enhance the energy of stable spectral features of residual convolution. This is conducive to subtly represent the inherent characteristics of the targets. Moreover, a feature classification approach based on one-dimensional convolution is applied to recognize targets. We evaluate our approach on challenging data containing four kinds of underwater acoustic targets with different working conditions. Our experiments show that the proposed approach achieves the best recognition accuracy (98.2%) compared with the other approaches. Moreover, the proposed approach is better than the ResNet with a widely used channel attention mechanism for data with different working conditions. Full article

The effective estimation of mixed-layer depth (MLD) plays a significant role in the study of ocean dynamics and global climate change. However, the methods of estimating MLD still have limitations due to the sparse resolution of the observed data. In this study, a hybrid estimation method that combines the K-means clustering algorithm and an artificial neural network (ANN) model was developed using sea-surface parameter data in the Indian Ocean as a case study. The oceanic datasets from January 2012 to December 2019 were obtained via satellite observations, Argo in situ data, and reanalysis data. These datasets were unified to the same spatial and temporal resolution (1° × 1°, monthly). Based on the processed datasets, the K-means classifier was applied to divide the Indian Ocean into four regions with different characteristics. For ANN training and testing in each region, the gridded data of 84 months were used for training, and 12-month data were used for testing. The ANN results show that the optimized NN architecture comprises five input variables, one output variable, and four hidden layers, each of which has 40 neurons. Compared with the multiple linear regression model (MLR) with a root-mean-square error (RMSE) of 5.2248 m and the HYbrid-Coordinate Ocean Model (HYCOM) with an RMSE of 4.8422 m, the RMSE of the model proposed in this study was reduced by 27% and 22%, respectively. Three typical regions with high variability in their MLDs were selected to further evaluate the performance of the ANN model. Our results showed that the model could reveal the seasonal variation trend in each of the selected regions, but the estimation accuracy showed room for improvement. Furthermore, a correlation analysis between the MLD and input variables showed that the surface temperature and salinity were the main influencing factors of the model. The results of this study suggest that the pre-clustering ANN method proposed could be used to estimate and analyze the MLD in the Indian Ocean. Moreover, this method can be further expanded to estimate other internal parameters for typical ocean regions and to provide effective technical support for ocean researchers when studying the variability of these parameters. Full article

Identifying people’s identity by using behavioral biometrics has attracted many researchers’ attention in the biometrics industry. Gait is a behavioral trait, whereby an individual is identified based on their walking style. Over the years, gait recognition has been performed by using handcrafted approaches. However, due to several covariates’ effects, the competence of the approach has been compromised. Deep learning is an emerging algorithm in the biometrics field, which has the capability to tackle the covariates and produce highly accurate results. In this paper, a comprehensive overview of the existing deep learning-based gait recognition approach is presented. In addition, a summary of the performance of the approach on different gait datasets is provided. Full article

Hydrogen sulfide (H₂S) is known to participate in bacteria-induced inflammatory response in periodontal diseases. Therefore, it is necessary to quantify H₂S produced by oral bacteria for diagnosis and treatment of oral diseases including halitosis and periodontal disease. In this study, we introduce a paper-based colorimetric assay for detecting bacterial H₂S utilizing silver/Nafion/polyvinylpyrrolidone membrane and a 96-well microplate. This H₂S-sensing paper showed a good sensitivity (8.27 blue channel intensity/μM H₂S, R² = 0.9996), which was higher than that of lead acetate paper (6.05 blue channel intensity/μM H₂S, R² = 0.9959). We analyzed the difference in H₂S concentration released from four kinds of oral bacteria (Eikenella corrodens, Streptococcus sobrinus, Streptococcus mutans, and Lactobacillus casei). Finally, the H₂S level in Eikenella corrodens while varying the concentration of cysteine and treatment time was quantified. This paper-based colorimetric assay can be utilized as a simple and effective tool for in vitro screening of H₂S-producing ability of many bacteria as well as salivary H₂S analysis. Full article