The internet and related technologies have promoted the development of medical and health fields, especially remote diagnosis. As medical images may be stolen in the transmission process, the patient's personal in...
详细信息
The internet and related technologies have promoted the development of medical and health fields, especially remote diagnosis. As medical images may be stolen in the transmission process, the patient's personal information could be leaked. Aiming at the problem of privacy disclosure of colour medical images, a hybrid domain watermarking scheme based on improved differential evolution (DE) and the singular value block embedding (SVBE) is proposed in this study. Through this scheme, the image containing the patient's information is hidden in the patient's medical carrier image as a watermark. First, redistributed invariant lifting wavelet transform (RILWT), discrete wavelet transform (DWT), and singular value decomposition (SVD) are used to process the colour medical carrier image, and the high-frequency information in the integer wavelet domain of the watermark is embedded into the processed carrier image using the proposed singular value block embedding method based on the improved differential evolution algorithm. At the same time, to increase the security of the watermark scheme, a digital signature based on the SHA-384 hash function is designed for verification before watermark extraction. Compared with recent related research, the scheme has strong invisibility and robustness.
Acoustic word embedding (AWE) has become a mainstream method in low-resource Query-by-Example keywords search. This letter proposes an AWE based on a multi-head attention quadruplet network, which can learn the attent...
详细信息
Acoustic word embedding (AWE) has become a mainstream method in low-resource Query-by-Example keywords search. This letter proposes an AWE based on a multi-head attention quadruplet network, which can learn the attention weight sequence for all time frames of bidirectional Long Short-Term Memory by a multi-head self-attentive mechanism to pay attention to the time position information. At the same time, we construct a differences order quadruplet loss to train the AWE model to adequately consider the relative and absolute distances between the positive and negative sample pairs. In addition, attention mechanism, differences order quadruplet loss, and word label information are combined to design an objective function so that the AWE vectors have a better feature expression in the embedded space. The experimental results show that the proposed method can improve the learning ability of the network and make the AWEs more identifiable. The above two points result in better performance in the word discrimination task.
Bionic electronic skin (e-skin) with intrinsic compressibility and stretchability holds significant potential in robotic haptics, enabling robots to perceive and interact with objects of various shapes effectively. Ho...
详细信息
Bionic electronic skin (e-skin) with intrinsic compressibility and stretchability holds significant potential in robotic haptics, enabling robots to perceive and interact with objects of various shapes effectively. However, creating a biomimetic e-skin with precise dual-signal decoupling remains a challenge. To address this, we present a bifunctional sensor inspired by the spider-hunting mechanism, which captures signals during predation. This sensor is constructed using pressure-stretched multilayer electrospinning of nanofibers-polyvinyl alcohol (CNC-PVA), followed by gas-phase polypyrrole (PPy) polymerization. The innovative superimposed design of the homologous multilayer sensing module, combined with a conductive nanofiber network structure, enables remarkable multi-signal self-decoupling capabilities. key features of this sensor include high-pressure sensitivity (14.8 kPa -1 for 0-21 kPa) and an impressively fast response time of 57 ms. As a pressure sensor, it demonstrates repeatability over 5 cycles, while as a stretching sensor, it achieves high sensitivity (gauge factor, GF=1.22) and remains stable over 1000 cycles. Furthermore, this self-decoupled sensing system can independently detect dual signals (shape and weight of objects), thereby empowering robots to recognize and handle various objects more effectively. This multifunctional, low-cost sensor offers an advanced solution to overcome problems in functional e-skin for enhanced robotic object manipulation and recognition capabilities.
Remote sensing image change detection plays a critical role in applications like video surveillance and geographic information systems. However, existing binary and semantic change detection (SCD) methods often rely s...
详细信息
Remote sensing image change detection plays a critical role in applications like video surveillance and geographic information systems. However, existing binary and semantic change detection (SCD) methods often rely solely on visual information, neglecting language information, which limits interpretability and the ability to provide specific change details. This work proposes the change knowledge-guided vision-language (VL) remote sensing change detection (CKCD) method to address these limitations. By introducing change knowledge as language information, CKCD enhances semantic understanding and change detail representation. A cross-modal affinity (CMA) module is designed to effectively fuse visual and textual features, improving information complementarity and fusion coherence. CKCD further enhances data utilization efficiency by merging change area detection and change category information into a single output through end-to-end learning. This design reduces redundant data representations and simplifies the detection process, leading to a more compact and efficient use of the input data without requiring additional branches or multiple output heads. Experimental results demonstrate consistent performance improvements over traditional methods across multiple change detection datasets.
The interface performance between composite reinforced concrete (RC) beams and TRC permanent formwork significantly influences the load-bearing capacity of composite beams. Based on bending tests of composite beams wi...
详细信息
The interface performance between composite reinforced concrete (RC) beams and TRC permanent formwork significantly influences the load-bearing capacity of composite beams. Based on bending tests of composite beams with varying dimensions, a numerical model considering the interface characteristics between concrete and formwork was established. The effects of member size, interface treatment, formwork shape, and the number of textile layers on the flexural behavior of composite beams were analyzed. Results indicate that as the size of composite beams increases, the interface transitions from localized microcracking to extensive debonding, altering the failure mode from bending to interface failure. For composite beams with U-shaped formwork and interfaces treated with cement paste, the load-bearing capacity increased by 16.78 %, 15.29 %, and 11.97 % for small-, medium-, and large-sized beams, respectively, compared to RC beams. This increase was approximately 10 % higher than that of composite beams with P-shaped formwork. Roughening the interface increased load-bearing capacity of composite beams by 5%- 8% compared to using cement paste at interface, while the insertion of shear pins into the roughened interface had a minimal further improvement. Each additional layer of textile in formwork boosted load-bearing capacity of the composite beams by approximately 3 %, with no significant rise beyond four layers. The interface slip fluctuated along the length of beams, with peak values concentrated in shear span. Ensuring effective bonding in this region is critical for enhancing the performance of composite beams. This study provides a foundation for the design and application of composite beams with permanent formwork.
PurposeDue to the structural layout, mining process, and working environment, curved chains such as horizontal and vertical bends inevitably exist in the armoured face conveyor (AFC). With the increasing power, convey...
详细信息
PurposeDue to the structural layout, mining process, and working environment, curved chains such as horizontal and vertical bends inevitably exist in the armoured face conveyor (AFC). With the increasing power, conveying capacity, and distance of the AFC, the dynamic influence of these curved chains should be highly emphasized. This paper establishes a dynamic model of the AFC by multi-body system theory and finite segment method, in which the curved chains can be fully ***/methodology/approachThe scraper chains are firstly grouped into the straight, horizontal bend, vertical convex and concave bend sections. Each bend section running in a circle is simplified as an ideal arc. Through solving its differential equilibrium equation and using Newton's second law, its running resistance is derived. Then the grouped chains are discretized into finite control elements according to the Kelvin model, and the governing equation of each control element is established. The dynamic model of the AFC is obtained by assembling these equations, and the corresponding simulation model is developed by using MATlab/*** studies with real scenarios are provided, and simulations are carried out. The results show that the running resistance contributed by the curved chains is larger than the traditional empirical ***/valueThe work in this paper helps the dynamic performance design of AFC, with a deep understanding of the curved chains.
Compared with powder metallurgy, centrifugal casting, jet molding, and other technologies, Laser Melting Deposition (LMD) stands out as an advanced additive manufacturing technology that provides substantial advantage...
详细信息
Compared with powder metallurgy, centrifugal casting, jet molding, and other technologies, Laser Melting Deposition (LMD) stands out as an advanced additive manufacturing technology that provides substantial advantages in the melt forming of functional gradient materials and composites. However, when high-temperature and high-speed laser energy is applied, the resulting materials are susceptible to porosity, which restricts their extensive use in fatigue-sensitive applications such as turbine engine blades, engine connecting rods, gears, and suspension system components. Since fatigue cracks generally originate near pore defects or at stress concentration points, it is crucial to investigate evaluation methods for pore defects and stress concentration in LMD applications. This study examines the effect of pore defects on stress concentration in LMD-manufactured AlSi10Mg using the crystal plasticity finite element method and proposes a stress concentration coefficient characterization approach that considers pore size, morphology, and location. The simulation results indicate a competitive mechanism between pores and grains, where the larger entity dominates. Regarding the influence of aspect ratio on stress concentration, as the aspect ratio decreases along the stress direction, the stress concentration increases significantly. When pores are just emerging from the surface (s/r = 1), the stress concentration caused by the pore reaches its maximum, posing the highest risk of material failure. To assess the extent to which the aspect ratio, position, and size of pores affect stress concentration, a statistical correlation analysis of these variables was conducted.
Inspired by the flexible skin of dolphins and the hydrophobic effect of lotus leaves, this study developed an adaptive drag reduction surface using biomimetic structures. The design combines a transverse groove base w...
详细信息
Inspired by the flexible skin of dolphins and the hydrophobic effect of lotus leaves, this study developed an adaptive drag reduction surface using biomimetic structures. The design combines a transverse groove base with hydrophobic flexible materials, employing hydraulic actuation for active surface morphing. This approach effectively integrates non-smooth structures, flexible surfaces, and hydrophobic drag reduction technologies, achieving up to 28 % drag reduction at a flow velocity of 0.2 m/s. This adaptive technology offers a robust solution for drag reduction across varying flow velocities in complex underwater environments.
In industrial settings with multiple robotic arms, ensuring human-robot interaction safety through visual feedback is essential. However, existing methods use multiple pre-set cameras to avoid occlusion, making implem...
详细信息
ISBN:
(纸本)9798350350920
In industrial settings with multiple robotic arms, ensuring human-robot interaction safety through visual feedback is essential. However, existing methods use multiple pre-set cameras to avoid occlusion, making implementation challenging in compact spaces. We propose an adaptive active visual perception method for safety in human-robot collaboration by equipping a single RGBD camera on an idle robotic arm. This method eliminates the need to add additional brackets, is low cost, and is suitable for compact environments compared to current methods. Firstly, to capture comprehensive and accurate global information as much as possible, an active visual perception strategy integrating static visual perception and proprioceptive pose optimization is designed;then, an optimization-based robot position and pose decision method is proposed by using the real-time robots state and obstacles state, which enables the camera at the end of the robot to acquire more effective views;finally, a dual-robot following strategy is proposed to ensure that it can work in tandem. The validity was proved by experimentation. The video are available at https://***/03lwb.
There is no precedent for the construction of large-section double-arch tunnels in fly ash accumulation stratum in China. The fly ash stratum is characterized by a loose structure, poor cementation, and low bearing ca...
详细信息
There is no precedent for the construction of large-section double-arch tunnels in fly ash accumulation stratum in China. The fly ash stratum is characterized by a loose structure, poor cementation, and low bearing capacity, which present significant challenges in tunnel design and construction. Based on the Yanpingba tunnel project, this paper conducts a model test on a large-section double-arch tunnel crossing a fly ash accumulation stratum, analyzing the tunnel's mechanical behavior under various sequential excavation methods. The results show a large settlement of the vault and upper stratum of the double-arch tunnel excavated in the fly ash accumulation stratum. In addition, the stratum can easily become unstable, so it is necessary to reinforce the stratum by grouting. Compared with the subsequent tunnel, the advance tunnel is more affected by excavation, and the risk of structural damage is higher. Compared with the central diaphragm (CD) method and the bench method, the single side drift method is more conducive to safe construction. A mid-partition wall can effectively reduce the settlement of the stratum, but it is easily deflected to the side by the bias pressure. Adding support on the side of the advance tunnel of the mid-partition wall is recommended.
暂无评论