Search

Stratospheric balloons serve as cost-effective platforms for wireless communication. However, these platforms encounter challenges stemming from their underactuation in the horizontal plane. Consequently, controllers must continually identify favorable wind conditions to optimize station-keeping performance while managing energy consumption. This study presents a receding horizon controller based on wind and balloon models. Two neural networks, PredRNN and ResNet, are utilized for short-term wind field forecast. Additionally, an online receding horizon controller, based on simultaneous optimistic optimization (SOO), is developed for action sequence planning and adapted to accommodate various constraints, which is especially suitable due to its gradient-free nature, high efficiency, and effectiveness in black-box function optimization. A reward function is formulated to balance power consumption and station-keeping performance. Simulations conducted across diverse positions and dates demonstrate the superior performance of the proposed method compared with traditional greedy and A* algorithms. [ABSTRACT FROM AUTHOR]

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis. [ABSTRACT FROM AUTHOR]

In order to indirectly calculate the core temperature of a cable joint, an equivalent transient thermal circuit model of single-core cable joint by considering axial heat dissipation is proposed. Firstly, the temperature field of the middle joint of a 110 kV single-core cable is calculated by finite element method. Based on the heat dissipation path of the core, an improved equivalent thermal circuit model is proposed. The axial heat dissipation of the cable joint core is simplified to a thermal resistance and the temperature rise of the cable body core, the temperature calculation of the cable joint transient process is realized. Compared with the results of finite element simulation, the steady-state temperature errors of the thermal circuit model are within 1 °C, while the maximum temperature errors of the transient process shall not exceed 3 °C, which proves the validity of the model. This method can provide reference for temperature inversion and the dynamic current-carrying capacity prediction of cable joints. [ABSTRACT FROM AUTHOR]

Prunus necrotic ringspot virus (PNRSV) is a significant virus of ornamental plants and fruit trees. It is essential to study this virus due to its impact on the horticultural industry. Several studies on PNRSV diversity and phytosanitary detection technology were reported, but the content on the codon usage bias (CUB), dinucleotide preference and codon pair bias (CPB) of PNRSV is still uncertain. We performed comprehensive analyses on a dataset consisting of 359 coat protein (CP) gene sequences in PNRSV to examine the characteristics of CUB, dinucleotide composition, and CPB. The CUB analysis of PNRSV CP sequences showed that it was not only affected by natural selection, but also affected by mutations, and natural selection played a more significant role compared to mutations as the driving force. The dinucleotide composition analysis showed an over-expression of the CpC/GpA dinucleotides and an under-expression of the UpA/GpC dinucleotides. The dinucleotide composition of the PNRSV CP gene showed a weak association with the viral lineages and hosts, but a strong association with viral codon positions. Furthermore, the CPB of PNRSV CP gene is low and is related to dinucleotide preference and codon usage patterns. This research provides reference for future research on PNRSV genetic diversity and gene evolution mechanism. [ABSTRACT FROM AUTHOR]

Link prediction is critical to completing the missing links in a network or to predicting the generation of new links according to current network structure information, which is vital for analyzing the evolution of a network, such as the logical architecture construction of MEC (mobile edge computing) routing links of a 5G/6G access network. Link prediction can provide throughput guidance for MEC and select appropriate c nodes through the MEC routing links of 5G/6G access networks. Traditional link prediction algorithms are always based on node similarity, which needs predefined similarity functions, is highly hypothetical and can only be applied to specific network structures without generality. To solve this problem, this paper proposes a new efficient link prediction algorithm PLAS (predicting links by analysis subgraph) and its GNN (graph neural network) version PLGAT (predicting links by graph attention networks) based on the target node pair subgraph. In order to automatically learn the graph structure characteristics, the algorithm first extracts the h-hop subgraph of the target node pair, and then predicts whether the target node pair will be linked according to the subgraph. Experiments on eleven real datasets show that our proposed link prediction algorithm is suitable for various network structures and is superior to other link prediction algorithms, especially in some 5G MEC Access networks datasets with higher AUC (area under curve) values. [ABSTRACT FROM AUTHOR]

Detecting fake reviews can help customers make better purchasing decisions and maintain a positive online business environment. In recent years, pre-trained language models have significantly improved the performance of natural language processing tasks. These models are able to generate different representation vectors for each word in different contexts, thus solving the challenge of multiple meanings of a word, which traditional word vector methods such as Word2Vec cannot solve, and, therefore, better capturing the text's contextual information. In addition, we consider that reviews generally contain rich opinion and sentiment expressions, while most pre-trained language models, including BERT, lack the consideration of sentiment knowledge in the pre-training stage. Based on the above considerations, we propose a new fake review detection model based on a pre-trained language model and convolutional neural network, which is called BSTC. BSTC considers BERT, SKEP, and TextCNN, where SKEP is a pre-trained language model based on sentiment knowledge enhancement. We conducted a series of experiments on three gold-standard datasets, and the findings illustrate that BSTC outperforms state-of-the-art methods in detecting fake reviews. It achieved the highest accuracy on all three gold-standard datasets—Hotel, Restaurant, and Doctor—with 93.44%, 91.25%, and 92.86%, respectively. [ABSTRACT FROM AUTHOR]

Currently, most recommendation algorithms only use a single type of user behavior information to predict the target behavior. However, when browsing and selecting items, users generate other types of behavior information, which is important, but often not analyzed or modeled by traditional recommendation algorithms. This study aims to design a multi-behavior recommendation algorithm based on graph neural networks by analyzing multiple types of behavior information in users' product purchasing process, to fully utilize multiple types of user behavior information. The algorithm models users, items, and user behavior in multiple dimensions by incorporating attention mechanisms and multi-behavior learning into graph neural networks, and solves the problem of imbalanced user behavior weights from the perspective of multi-task loss optimization. After experimental verification, we proposed that the multi-behavior graph attention network (MGAT) algorithm has better performance compared to four other classical recommendation algorithms on the Beibei and Taobao datasets. The results demonstrate that the multi-behavior recommendation algorithm based on graph neural networks has practicality in fully utilizing multiple types of user information, and can solve the problem of imbalanced user behavior weights to some extent. [ABSTRACT FROM AUTHOR]

The effect of laser-current delay on extreme ultraviolet emission by laser-triggered discharge-plasma has been investigated. Typical waveforms for current, voltage, laser signals, and X-ray signals have been compared. Theoretical tin spectra were simulated among the electron temperature ranges from 10 to 50 eV to compare with the experimental results. The results show that longer laser-current delay time is propitious to increase the steady-state time of plasma at high temperatures, and it increases the intensity and spectral purity of 13.5 nm emission in 2% band. The 13.5 nm radiation intensity increases about 120% with the delay increasing from 0.7 to 5 μs, and the extreme ultraviolet (EUV) emission conversion efficiency (CE) increases from 0.5% to 1.1%. [ABSTRACT FROM AUTHOR]

The lift of an aircraft can be effectively enhanced by circulation control (CC) technology at subsonic speeds, but the efficiency at transonic speeds is greatly decreased. The underlying mechanism of this phenomenon is not fully understood. In this study, Reynolds averaged Navier—Stokes simulation with k − ω shear stress transport model was utilized to investigate the mechanism of lift enhancement by CC in transonic flow. For validation, the numerical CC results were compared with the NASA experimental data obtained for transonic CC airfoil. Thereafter, the RAE2822 airfoil was modified with a Coanda surface. The lift enhancement effects of CC via steady blowing with different momentum coefficients were tested at M a = 0.3 and 0.8 at α = 3 ∘ , and various fluid mechanics phenomena were investigated. The results indicate that the flow structure of the CC jet is insensitive to the incoming flow conditions because of the similarity to the local static pressure field around the trailing edge of the airfoil. Owing to the appearance of shockwaves on the airfoil surface in the transonic regime, the performance of the CC jet is restricted to the trailing edge of the airfoil. Transonic CC achieved a slight improvement in aerodynamic performance owing to a favorable shift in the shockwave pattern and accelerated flow in the separation region on the airfoil surfaces. Revealing the mechanism of lift enhancement of CC in the transonic regime can facilitate the rational design of new fluidic actuators with high activity and expand the potential applications of CC technology. [ABSTRACT FROM AUTHOR]

Sugars are critical for plant growth and development as suppliers of carbon and energy, as signal molecules, or as solute molecules for osmotic homeostasis. Monosaccharide transporter (MST) genes are involved in various processes of plant growth and development as well as in response to abiotic stresses. However, the evolution and their roles of MST genes in growth and development and in coping with abiotic stresses in rice are poorly known. Here, we identified 64 MST genes in rice genome, which are classified into seven subfamilies: STP, PLT, AZT, ERD, pGlcT, INT, and XTPH. MST genes are not evenly distributed between chromosomes (Chrs) with a bias to Chr 3, 4, 7, and 11, which could be a result of duplication of fragments harboring MST genes. In total, 12 duplication events were found in the rice MST family, among which, two pairs were derived from fragmental duplications and ten pairs were from tandem duplications. The synonymous and nonsynonymous substitution rates of duplicate gene pairs demonstrated that the MST family was under a strong negative selection during the evolution process. Furthermore, a comprehensive expression analysis conducted in 11 different tissues, three abiotic stresses, five hormone treatments, and three sugar treatments revealed different expression patterns of MST genes and indicated diversified functions of them. Our results suggest that MST genes play important roles not only in various abiotic stresses but also in hormone and sugar responses. The present results will provide a vital insight into the functional divergence of the MST family in the future study. [ABSTRACT FROM AUTHOR]