Search

Detecting and recognizing pests are paramount for ensuring the healthy growth of crops, maintaining ecological balance, and enhancing food production. With the advancement of artificial intelligence technologies, traditional pest detection and recognition algorithms based on manually selected pest features have gradually been substituted by deep learning-based algorithms. In this review paper, we first introduce the primary neural network architectures and evaluation metrics in the field of pest detection and pest recognition. Subsequently, we summarize widely used public datasets for pest detection and recognition. Following this, we present various pest detection and recognition algorithms proposed in recent years, providing detailed descriptions of each algorithm and their respective performance metrics. Finally, we outline the challenges that current deep learning-based pest detection and recognition algorithms encounter and propose future research directions for related algorithms. [ABSTRACT FROM AUTHOR]

The stability of the output speed of a hydraulic system has a great influence on the working performance of hydraulic equipment. It changes with the system working conditions. The increase in leakage caused by the wear of the hydraulic kinematic pair and the slip of the motor lead to the instability of the output speed. Although the hydraulic system can satisfy the output requirements of the active control scheme with ex ante decision making or the passive feedback control strategy with ex post compensation, it also causes an increase in system complexity and manufacturing cost. The speed stiffness as a basic characteristic of the output of the hydraulic system has not been sufficiently investigated and evaluated. In this paper, the IFMDH (inverter-fed, motor-driven hydraulic) system is taken as the object, and the coupling relationship of each link of the system is revealed by mathematical modelling. The reliability of the model is verified under a wide range of speed and load variations in combination with experiments. By redefining the speed stiffness quantification method, the effects of load conditions, motor stiffness, and speed ratio at the output end on the speed stability of the system are discussed in conjunction with the system coupling mechanism model. The conclusions show that the motor stiffness and the addition of a speed reducer have a significant effect on the system speed stiffness, where changing the output speed ratio has a significant effect on the speed stiffness. The conclusions of the study provide technical support for the rapid design, selection, and system optimisation of hydraulic systems in common scenarios. [ABSTRACT FROM AUTHOR]

Fitness yoga is now a popular form of national fitness and sportive physical therapy. At present, Microsoft Kinect, a depth sensor, and other applications are widely used to monitor and guide yoga performance, but they are inconvenient to use and still a little expensive. To solve these problems, we propose spatial–temporal self-attention enhanced graph convolutional networks (STSAE-GCNs) that can analyze RGB yoga video data captured by cameras or smartphones. In the STSAE-GCN, we build a spatial–temporal self-attention module (STSAM), which can effectively enhance the spatial–temporal expression ability of the model and improve the performance of the proposed model. The STSAM has the characteristics of plug-and-play so that it can be applied in other skeleton-based action recognition methods and improve their performance. To prove the effectiveness of the proposed model in recognizing fitness yoga actions, we collected 960 fitness yoga action video clips in 10 action classes and built the dataset Yoga10. The recognition accuracy of the model on Yoga10 achieves 93.83%, outperforming the state-of-the-art methods, which proves that this model can better recognize fitness yoga actions and help students learn fitness yoga independently. [ABSTRACT FROM AUTHOR]

Porous gold with well-defined shape and size have aroused extensive research enthusiasm due to their prominent properties in various applications. However, it is still a great challenge to explore a simple, green, and low-cost route to fabricate porous gold with a "clean" surface. In this work, porous worm-like Au has been easily synthesized in a one-step procedure from aqueous solution at room temperature under the action of ionic liquid tetrapropylammonium glycine ([N3333][Gly]). It is shown that the as-prepared porous worm-like Au has the length from 0.3 to 0.6 μm and the width of approximately 100–150 nm, and it is composed of lots of small nanoparticles about 6–12 nm in diameter. With rhodamine 6G (R6G) as a probe molecule, porous worm-like Au displays remarkable surface enhanced Raman scattering (SERS) sensitivity (detection limit is lower than 10−13 M), and extremely high reproducibility (average relative standard deviations is less than 2%). At the same time, owing to significantly high specific surface area, various pore sizes and plenty of crystal defects, porous worm-like Au also exhibits excellent catalytic performance in the reduction of nitroaromatics, such as p-nitrophenol and p-nitroaniline, which can be completely converted within only 100 s and 150 s, respectively. It is expected that the as-prepared porous worm-like Au with porous and self-supported structures will also present the encouraging advances in electrocatalysis, sensing, and many others. [ABSTRACT FROM AUTHOR]

The reversible phase transfer of compounds between two immiscible liquid phases has many applications in a wide range of fields, and ionic liquids have been widely used as potential functional solvents and catalysts. However, photo-triggered reversible phase transfer of ionic liquids between the organic phase and water phase has not been reported so far. In the present work, the reversible phase transfer of six kinds of azobenzene-based ionic liquid surfactants between the organic phase and water phase is investigated by alternative irradiation of UV and visible light. Factors affecting the transfer efficiency, such as chemical structure and concentration of the ionic liquid surfactants, equilibrium photo-isomerization degree, and the aggregation state of ionic liquid surfactants are investigated in detail. It is shown that transfer efficiency greater than 89% was achieved under optimal conditions, equilibrium photo-isomerization degree of the ionic liquid surfactants is the main factor to determine their transfer efficiencies, and the aggregation of cis-isomers is not beneficial for the transfer. [ABSTRACT FROM AUTHOR]

Recently, the efficient chemical fixation of carbon dioxide (CO2) into high value chemicals without using noble metal catalysts has become extremely appealing from the viewpoint of sustainable chemistry. In this work, a one-pot three component reaction of propargylic alcohols, anines and CO2 that can proceed in an atom economy and environmentally benign manner by combination of CuI and tetrabutylphosphonium imidazol ([P4444][Im]) as a catalyst was described. Catalysis studies indicate that this catalytic system is an effective catalyst for the conversion of CO2 into oxazolidinones at room temperature and ambient pressure without any solvent. The results provide a useful way to design novel noble metal-free catalyst systems for the transformation of CO2 into other valuable compounds. [ABSTRACT FROM AUTHOR]