Enhancing zero-shot relation extraction with a dual contrastive learning framework and a cross-attention module by Diyou Li, Lijuan Zhang, Jie Huang, Neal Xiong, Lei Zhang, Jian Wan

“…However, the existing ZSRE models ignore the importance of semantic information fusion and possess limitations when used for zero-shot relation extraction tasks. …”
Get full text

Beam Shaping by Mode Superposition With Coefficient Optimization by Guowen Zhang, Hang Sun, Ziyang Chen, Yanli Zhang, Jixiong Pu, Jianqiang Zhu

“…Beam shaping is of significance for applications in various fields, including laser fusion, laser processing, and optical manipulation. …”
Get full text

Deep learning‐based unmanned aerial vehicle detection in the low altitude clutter background by Zeyang Wu, Yuexing Peng, Wenbo Wang

“…Thereafter, a contrastive‐learning‐based feature extraction and fusion unit is established to suppress non‐target clutter interference and extract recognisable semantic UAV features. …”
Get full text

Efficiently Modeling Lateral Vehicle Movement Including its Temporal Interrelations Using a Two-Level Stochastic Model by N. Neis, J. Beyerer

Get full text

Residential Electrical Load Forecasting Based on a Real-Time Evidential Time Series Prediction Method by M. Mroueh, M. Doumiati, C. Francis, M. Machmoum

“…The proposed method employs information fusion techniques to combine multiple predictors, each with its own forecasting mechanism. …”
Get full text

Research on Medium and Long-Term Runoff Forecast of Xijiang River in Dry Season Based on Statistical Model by LAN Yuxi, ZHANG Yin, NONG Zhenchang, WEI Yongjiang

“…Accurate medium and long-term runoff forecast is of great guiding significance to the development and utilization of water resources,allocation optimization,and water dispatch.Based on the three statistical models of mean generating function,periodic analysis,and multiple stepwise regression,this paper studied the medium and long-term runoff forecast of the Longtan Reservoir in the upper reaches of the Xijiang River and the Wuzhou hydrological station in the lower reaches from October to March of the following year and during the entire dry season (six months,from October to March of the following year).The results show that the three models all present positive forecast results.In the calibration and verification periods,the average pass rate exceeds 75%,and the mean absolute percentage error is basically within 30%.The forecast accuracy of the mean generating function and the multiple stepwise regression is significantly higher than that of the periodic analysis,with smaller forecast errors in larger values.Multiple stepwise regression is more stable than the other two models.Furthermore,affected by the consistency of data,the forecast accuracy of the Longtan Reservoir is significantly higher than that of the Wuzhou hydrological station.On the whole,multiple stepwise regression has the optimal forecast effect in the Xijiang River Basin.In addition,it can maintain high forecast accuracy at all levels and stages and provide a valuable reference for water dispatch decisions in the basin.In the future,multi-model fusion can be used to further improve the forecast effect.…”
Get full text

Joint Nonnegative Matrix Factorization Based on Sparse and Graph Laplacian Regularization for Clustering and Co-Differential Expression Genes Analysis by Ling-Yun Dai, Rong Zhu, Juan Wang

“…First, SG-jNMF1 projects multiomics data into a common subspace and applies the multiomics fusion characteristic matrix to mine the important information closely related to diseases. …”
Get full text

Synthesis and Antibacterial Activity of Some New Phenothiazine Derivatives by Pawan Kumar Swarnkar, P. Kriplani, G. N. Gupta, K. G. Ojha

“…This synthesis besides by using conventional methods was also attempted using microwave. Fusion of 5 with sulphur in presence of iodine results in α-(2-diazo-6-substituted benzothiazolyl)-6- substituted [2, 3-b] benzophenothiazines(6). …”
Get full text

Unusual Painful Muscle Spasm in a Dialysis-Dependent Patient with Progressive Cervical Kyphosis by Daisuke Tsunoda, Yoichi Iizuka, Tokue Mieda, Haku Iizuka, Hirotaka Chikuda

“…The patient underwent 2-stage circumferential decompression and fusion. After the revision procedure, his symptoms improved, and his serum CK level normalized. …”
Get full text

Daily Activity Monitoring and Fall Detection Based on Surface Electromyography and Plantar Pressure by Xugang Xi, Wenjun Jiang, Zhong Lü, Seyed M. Miran, Zhi-Zeng Luo

“…Suitable features were selected and combined for posture transition, gait, and fall using the Fisher class separability index. A feature-level fusion method, named as the global canonical correlation analysis of weighting genetic algorithm, was proposed to reduce dimensions. …”
Get full text

A Perspective Review on Thermal Conductivity of Hybrid Nanofluids and Their Application in Automobile Radiator Cooling by Wisdom Etabiese Ukueje, Fidelis Ibiang Abam, Anthony Obi

“…Hybrid nanofluids developed with the fusion or suspension of two or more different nanoparticles in a mixture as a novel heat transfer fluid are currently of interest to researchers due to their proven better measured thermal conductivities. …”
Get full text

Current State of Type 1 Diabetes Immunotherapy: Incremental Advances, Huge Leaps, or More of the Same? by Brett Phillips, Massimo Trucco, Nick Giannoukakis

“…The majority of these immunomodulators are humanised antibodies that target immune cells or cytokines. These as well as fusion proteins and inhibitor proteins all share varying adverse event occurrence and severity. …”
Get full text

A Small Target Detection Method Based on the Improved FCN Model by Guofeng Ma

“…The traditional method based on multilayer feature fusion cannot achieve ideal results for STD. This study is based on FCN and introduces a spatial transformation network. …”
Get full text

Abstract visual reasoning based on algebraic methods by Mingyang Zheng, Weibing Wan, Zhijun Fang

“…This paper constructs a relation model with object-centric inductive biases, learning end-to-end multi-granular rule embeddings at different levels. Through a gating fusion module, the model incrementally integrates explicit representations of objects and abstract relationships. …”
Get full text

Topology optimization applied to additive-manufactured hydrofoil wing components by Margarida Mata, Ricardo Bencatel, Elsa W. Sequeiros, Manuel F. Vieira, Jose M. Costa

“…Hydrofoils, characterized by their hydrodynamic shape, generate lift forces that elevate the boat above the water, enhancing its speed. Utilizing Fusion 360, a mechanism was designed to adjust the angle of attack of the hydrofoil wings. …”
Get full text

Elevated high-precision mapping and localization technology for periodic inspections by Xianghua Fan, Wenbo Pan

“…Multiple experiments conducted in subway tunnel scenarios demonstrate the robust trajectory estimation capability of the proposed method in long tunnel scenarios, showcasing clear advantages over classical multi-sensor fusion methods prone to failure due to sensor degradation. …”
Get full text

Cellular Immunogenicity of Novel Gene Immunogens in Mice Monitored by in Vivo Imaging by Elizaveta Starodubova, Olga Krotova, David Hallengärd, Yulia Kuzmenko, Gunnel Engström, Diana Legzdina, Oleg Latyshev, Olesja Eliseeva, Anna Karin Maltais, Vera Tunitskaya, Vadim Karpov, Andreas Bråve, Maria Isaguliants

“…Both immune and in vivo imaging techniques concordantly demonstrated an enhanced immunogenicity of RT-LAMP and of the N-terminal Gly-Ala-RT fusion genes. In vivo imaging performed as an animal-sparing method to estimate the overall performance of DNA immunogens, predicting it early in the experiment. …”
Get full text

High-Accuracy and Low-Cost Attitude Measurement Unit of the CubeSat by Haining Ma, Zhengliang Lu, Xiang Zhang, Wenhe Liao, Klaus Briess

“…The Multiplicative Extended Kalman Filter (MEKF) is used to estimate the attitude of CubeSat, and four kinds of attitude estimation layouts are put forward according to the idea of weighted average of two quaternions from two STR and different architectures of information fusion. Using the proposed methods, the attitude measurement unit can continuously provide accurate and reliable attitude knowledge for attitude control unit when the CubeSat is running in orbit. …”
Get full text

Drug-target binding affinity prediction based on power graph and word2vec by Jing Hu, Shuo Hu, Minghao Xia, Kangxing Zheng, Xiaolong Zhang

“…Conclusions In this model, the drug molecular features in the power graph module are extracted by a graph neural network, and then the protein features are obtained by the Word2vec method. After feature fusion, they are input into the three full connection layers to obtain the drug target affinity prediction value. …”
Get full text

The Fetal Allograft Revisited: Does the Study of an Ancient Invertebrate Species Shed Light on the Role of Natural Killer Cells at the Maternal-Fetal Interface? by Amy Lightner, Danny J. Schust, Yi-Bin A. Chen, Breton F. Barrier

“…Chimeric combination in B. schlosseri results in vascular fusion between two individual colonies; uterine NK cells appear essential to the establishment of adequate maternal-fetal circulation. …”
Get full text