Search

Data information security on wearable devices has emerged as a significant concern among users, so it becomes urgent to explore authentication methods based on wearable devices. Using PhotoPlethysmoGraphy (PPG) signals for identity authentication has been proven effective in biometric authentication. This paper proposes a convolutional neural network authentication method based on 2D PPG signals applied to wearable devices. This method uses Markov Transition Field technology to convert one-dimensional PPG signal data into two-dimensional image data, which not only retains the characteristics of the signal but also enriches the spatial information. Afterward, considering that wearable devices usually have limited resources, a lightweight convolutional neural network model is also designed in this method, which reduces resource consumption and computational complexity while ensuring high performance. It is proved experimentally that this method achieves 98.62% and 96.17% accuracy on the training set and test set, respectively, an undeniable advantage compared to the traditional one-dimensional deep learning method and the classical two-dimensional deep learning method.

Background: It is adverse for the safety of a tailings dam to use fine-grained tailings as the materials for a high tailings dam because of the low penetration coefficient, the slow consolidating velocity, and the bad physical mechanical property. Furthermore, with the influence of complicated geography conditions, the phreatic line will be increased enormously when encountering special conditions, which directly affect the safe operation of the tailings dam. Methods: In this study, based on the engineering, geological, and hydrogeological conditions and survey results of a tailings dam, a 210 m fine-grained tailings dam located in three gullies was selected and used to simulate the three-dimensional seepage field of a tailings dam under a steady saturated state by using the finite element software MIDAS GTS. The permeability coefficient was inverted, the seepage field of the project under different working conditions was simulated, and the position of the phreatic line was obtained. The controlled position of phreatic lines was determined by combining the seepage field with the stability requirements. Results: Back analysis could accurately reflect the actual permeability coefficient of each partition of tailings dams. Due to the multiple areas of seepage accumulation, large valley corners, and narrowing of the dam axis, the phreatic line of the shoulder region was elevated by 2~3 m compared to the surrounding area and was thereby the most critical region of the tailings dam seepage control. The stability requirements and minimum controlled position of the phreatic line requirements could be met when the controlled position of the phreatic line was 23 m. Conclusion: This study revealed the key areas and reasons why the tailings dam’s phreatic line is prone to be uplifted under complicated geography conditions. It was very critical to control the local phreatic line by adopting local horizontal seepage drainage measures or radiation wells in the key areas of the tailings dam to ensure the safety of the tailings dam. In addition to strengthening the daily monitoring of the key areas and the exfiltration facilities of the tailings dam, it is recommended to carry out determination tests of the permeability coefficient and particle size at regular intervals. The findings could provide countermeasures for seepage control.

In this study, we address the limitations of current deep learning models in road extraction tasks from remote sensing imagery. We introduce MixerNet-SAGA, a novel deep learning model that incorporates the strengths of U-Net, integrates a ConvMixer block for enhanced feature extraction, and includes a Scaled Attention Gate (SAG) for augmented spatial attention. Experimental validation on the Massachusetts road dataset and the DeepGlobe road dataset demonstrates that MixerNet-SAGA achieves a 10% improvement in precision, 8% in recall, and 12% in IoU compared to leading models such as U-Net, ResNet, and SDUNet. Furthermore, our model excels in computational efficiency, being 20% faster, and has a smaller model size. Notably, MixerNet-SAGA shows exceptional robustness against challenges such as same-spectrum–different-object and different-spectrum–same-object phenomena. Ablation studies further reveal the critical roles of the ConvMixer block and SAG. Despite its strengths, the model’s scalability to extremely large datasets remains an area for future investigation. Collectively, MixerNet-SAGA offers an efficient and accurate solution for road extraction in remote sensing imagery and presents significant potential for broader applications.

With the increasing demand for intelligent custom clothing, the development of highly accurate human body dimension prediction tools using artificial neural network technology has become essential to ensuring high-quality, fashionable, and personalized clothing. Although support vector regression (SVR) networks have demonstrated state-of-the-art (SOTA) performances, they still fall short on prediction accuracy and computation efficiency. We propose a novel generalized regression forecasting network (GRFN) that incorporates kernel ridge regression (KRR) within a multi-strategy multi-subswarm particle swarm optimizer (MMPSO)-SVR nonlinear regression model that applies a residual correction prediction mechanism to enhance prediction accuracy for body dimensions. Importantly, the predictions are generated using only a few basic body size parameters from small-batch samples. The KRR regression model is employed for preliminary residual sequence prediction, and the MMPSO component optimizes the SVR parameters to ensure superior correction of nonlinear relations and noise data, thereby yielding more accurate residual correction value predictions. The GRFN hybrid model is superior to SOTA SVR models and increases the root mean square performance by 91.73–97.12% with a remarkably low mean square error of 0.0054 ± 0.07. This outstanding advancement sets the stage for marketable intelligent apparel design tools for the fast fashion industry.

Road extraction from high-resolution satellite images has become a significant focus in the field of remote sensing image analysis. However, factors such as shadow occlusion and spectral confusion hinder the accuracy and consistency of road extraction in satellite images. To overcome these challenges, this paper presents a multi-scale fusion-based road extraction framework, HRU-Net, which exploits the various scales and resolutions of image features generated during the encoding and decoding processes. First, during the encoding phase, we develop a multi-scale feature fusion module with upsampling capabilities (UMR module) to capture fine details, enhancing shadowed areas and road boundaries. Next, in the decoding phase, we design a multi-feature fusion module (MPF module) to obtain multi-scale spatial information, enabling better differentiation between roads and objects with similar spectral characteristics. The network simultaneously integrates multi-scale feature information during the downsampling process, producing high-resolution feature maps through progressive cross-layer connections, thereby enabling more effective high-resolution prediction tasks. We conduct comparative experiments and quantitative evaluations of the proposed HRU-Net framework against existing algorithms (U-Net, ResNet, DeepLabV3, ResUnet, HRNet) using the Massachusetts Road Dataset. On this basis, this paper selects three network models (U-Net, HRNet, and HRU-Net) to conduct comparative experiments and quantitative evaluations on the DeepGlobe Road Dataset. The experimental results demonstrate that the HRU-Net framework outperforms its counterparts in terms of accuracy and mean intersection over union. In summary, the HRU-Net model proposed in this paper skillfully exploits information from different resolution feature maps, effectively addressing the challenges of discontinuous road extraction and reduced accuracy caused by shadow occlusion and spectral confusion factors. In complex satellite image scenarios, the model accurately extracts comprehensive road regions.

In view of the problems of rapid construction and deformation control of large cross-section tunnels in complex urban environments, the concept of “timely high-strength support” was put forward to form strong support over time and bear the load of surrounding rock in real time, and innovatively developed the spatial reticulated grid bolt-shotcrete support structure (SRGB). The research in this paper focuses on the supporting principle, bearing mechanical properties, snatch simulation test, construction process, and engineering application effects. The components of the SRGB and their respective functions were expounded in detail. The failure modes and deformation characteristics of the tested components were revealed through the indoor loading test, and the performance characteristics of the spatial reticulated grid concrete components with high strength and high rigidity were displayed. With the help of the multi-functional operation trolley, the assembly process test of the spatial reticulated grid was carried out, which verified the feasibility of mechanized construction and the rationality of structural design. Relying on the underground tunnel project of Guangzhou Metro, the spatial reticulated grid structure was successfully used as the initial support of the tunnel for the first time, forming a complete set of mechanized rapid construction technology for a large cross-section tunnel, and constructing a timely high-strength support system suitable for the complex urban environment. The research results provide a new idea and new technology for the mechanized rapid construction and efficient support of large cross-section tunnels.

To solve the technical problems of slow construction progress, low mechanization and high risk of shallow buried large cross-section tunnels in a complex urban environment, a series of spatial reticulated shell (SRS) support structures are developed in this paper. Moreover, the equipment of a multifunctional operation trolley is developed to install the SRS arch, and the construction technology system of the prefabricated SRS structure is proposed for a large cross-section tunnel. Therefore, the deformation characteristics of the end-plate joint component and jointless component are clarified by laboratory experiments. The construction mechanics’ simulation of the SRS arch is performed to obtain the tunnel deformation and structure stress based on the tunnel project of Panyu Square Station of Guangzhou Metro. A field application of the prefabricated SRS arch is carried out to realize the mechanized construction operation. The obtained results reveal that the end-plate joint component has better ductility, and its ultimate bearing capacity is basically consistent with the jointless component. The SRS arch can effectively control the deformation of the surrounding rock, improve the stress state of the structure, and reduce the plastic zone of shotcrete by numerical simulations. The overall stress of the SRS arch by field measurement represents the characteristics of “bigger on the upside and smaller on the downside” and “uneven symmetry”. Additionally, the successful application of the prefabricated SRS arch provides a scientific reference for mechanized construction of large cross-section tunnels.

This paper presents a supervised reinforcement learning (SRL)-based framework for longitudinal vehicle dynamics control of cooperative adaptive cruise control (CACC) system. A supervisor network trained by real driving data is incorporated into the actor-critic reinforcement learning approach. In the SRL training process, the actor and critic network are updated under the guidance of the supervisor and the gain scheduler. As a result, the training success rate is improved, and the driver characteristics can be learned by the actor to achieve a human-like CACC controller. The SRL-based control policy is compared with a linear controller in typical driving situations through simulation, and the control policies trained by drivers with different driving styles are compared using a real driving cycle. Furthermore, the proposed control strategy is demonstrated by a real vehicle-following experiment with different time headways. The simulation and experimental results not only validate the effectiveness and adaptability of the SRL-based CACC system, but also show that it can provide natural following performance like human driving.

In order to enhance the practicality of multi-wavelength erbium-doped fiber lasers (MWEDFLs), a novel hybrid dual-ring configuration is proposed in this article, which can flatten the outputs through an optical nonlinear-polarization-rotation-based ring cavity and stabilize the shifts of power and central wavelength of oscillations through an electrical fuzzy-control-based feedback. The experiment results show that, our scheme achieves more than 10 stable oscillations with the dramatic improvements in flatness and working stability. Under dual-ring configuration, the output intensity of MWEDFL reaches ~−7.5 dBm with the flatness of ±0.42 dB. And the in-stabilities in terms of power and central wavelength are respectively constrained ±0.182 dBm and ±0.029 nm within 10-h continuous operation.

The effect of vehicle active safety systems is subject to the accurate knowledge of vehicle states. Therefore, it is of great importance to develop a precise and robust estimation approach so as to deal with nonlinear vehicle dynamics systems. In this paper, a planar vehicle model with a simplified tire model is established first. Two advanced model-based estimation algorithms, an unscented Kalman filter and a moving horizon estimation, are developed for distributed drive electric vehicles. Using the proposed algorithms, vehicle longitudinal velocity, lateral velocity, yaw rate as well as lateral tire forces are estimated based on information fusion of standard sensors in today’s typical vehicle and feedback signals from electric motors. Computer simulations are implemented in the environment of CarSim combined with Matlab/Simulink. The performance of both estimators regarding convergence, accuracy, and robustness against an incorrect initial estimate of longitudinal velocity is compared in detail. The comparison results demonstrate that both estimation approaches have favourable coincidence with the corresponding reference values, while the moving horizon estimation is more accurate and robust, and owns faster convergence.