Purpose This study aimed to identify risk factors for right recurrent laryngeal nerve lymph node (RRLNLN) metastasis using computed tomography (CT) imaging histology and clinical data from patients with esophageal squamous cell carcinoma (ESCC), ultimately developing a prediction model. Methods Data were collected 370 who underwent surgical resection at the Department of Thoracic Surgery, Zhongshan Hospital Xiamen University, December 2014 2020. Subsequently, venous-stage chest-enhanced CT...

Power transformers are important pieces of equipment for the operation power systems. Accurate diagnosis their fault is closely related to stable entire grid. In order improve diagnostic accuracy transformer fault, grey wolf optimization (GWO) algorithm introduced, and differential evolution mechanism integrated into algorithm. Therefore, this paper proposes a method based on modified (MGWO) support vector machine (SVM), so that application realizes penalty factor kernel parameter in SVM....

Signal detection is crucial in multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, yet classical methods often struggle with nonlinear issues wireless channels. To handle this challenge, we propose a novel signal method for MIMO-OFDM system based on the fractional Fourier transform (FrFT), leveraging robust time series processing capabilities of long short-term memory (LSTM) networks. Our innovative approach, termed IM-LSTMNet, integrates LSTM...

A new method for fault location of a power distribution network based on Improved Cuckoo Search Algorithm is proposed. uses Lévy flight to simulate the global parasitic propagation mechanism cuckoo population. Therefore, algorithm avoids falling into local optimum easily. According requirements quickness and accuracy location, improved by combining search step size number iterations. It improves algorithm's early iteration speed subsequent accuracy. In this paper, used generate random status...

The integration of graph embedding technology and collaborative filtering algorithms has shown promise in enhancing the performance recommendation systems. However, existing integrated often suffer from feature bias lack effectiveness personalized user recommendation. For instance, users’ historical interactions with a certain class items may inaccurately lead to recommendations all within that class, resulting bias. Moreover, accommodating changes interests over time poses significant...

In the context of global climate change, air quality prediction work has a substantial impact on humans’ daily lives. The current extensive usage machine learning models for forecasting resulted in significant improvements to sector. long short-term memory network is deep model, which adds forgetting layer recurrent neural and several applications prediction. experimental data presented this research include pollution (SO2, NO2, PM10, PM2.5, O3, CO) meteorological (temperature, barometric...

Link prediction is recognized as a crucial means to analyze dynamic social networks, revealing the principles of relationship evolution. However, complex topology and temporal evolution characteristics networks pose significant research challenges. This study introduces an innovative fusion framework that incorporates entropy, causality, GCN model, focusing specifically on link in networks. Firstly, preprocesses raw data, extracting recording timestamp information between interactions. It...

Nonlinear simulations are devoted to the comparative study of equilibrium electrons' motion and stability in combination a three-dimensional helical wiggler positive or reversed guide magnetic field, where effects self-field, off-axis guiding center adiabatic field included. It is shown that configuration brings electron much smaller Larmor radius transverse displacement span than does, consequently, provides better transportation quality beam. Although far from resonance antiresonance...

Weyl almost automorphy is a natural generalization of Bochner and Stepanov automorphy. However, the space composed automorphic functions not Banach space. Therefore, results existence solutions differential equations are few, difference rare. Since study dynamic on time scales can unify equations. in this paper, we first propose concept then take Clifford‐valued shunt inhibitory cellular neural networks with time‐varying delays as an example to global exponential stability their solutions....

Hash is one of the most widely used methods for computing efficiency and storage efficiency. With development deep learning, hash method shows more advantages than traditional methods. This paper proposes a to convert entities with attribute information into embedded vectors (FPHD). The design uses quickly extract entity features, neural network learn implicit association between features. solves two main problems in large-scale dynamic data addition: (1) linear growth size vector table...

Irregular phase-space orbits of the electrons are harmful to electron-beam transport quality and hence deteriorate performance a free-electron laser (FEL). In previous literature, it was demonstrated that irregularity electron could be caused in several ways, such as varying wiggler amplitude inducing sidebands. Based on Hamiltonian model with set self-consistent differential equations, is shown this paper normalized plasma frequency functions not only couple motion FEL wave, which results...

To enhance the precision of rolling bearing fault detection and lessen likelihood safety mishaps, this paper proposes a method grounded in improved variational mode decomposition. This technique initially employs Northern Eagle Algorithm to determine optimal parameter value for decomposition, subsequently decomposing signal. is followed by utilization Spearman correlation coefficient differentiate between effective component noise-dominant component. Finally, wavelet packet decomposition...

In recent years, the UAV technology has developed rapidly and is widely used in military, civil scientific research fields. order to avoid external electromagnetic interference, bearings-only passive positioning method usually adjust position of maintain formation.In this study, according circular formation Uavs, model received signal Uavs on excellent arc inferior are established. The with slightly deviated positions effectively adjusted, receiving paper, double-station cross-positioning...

A novel wavelet packet based approach to Subband decomposition independent component analysis (SDICA) is proposed. The mutual information on small cumulant introduced select the with least dependent components. We present favorable comparisons WPSD ICA and other algorithm in extensive simulations. demonstrate consistent performance terms of accuracy robustness as well computational efficiency algorithm. Experimental results that proposed method can significantly improve face recognition performance.

Highway is an important symbol of measure the level modernization, its safety seriously affects people's lives and property. Combined with modern measurement control technology, communications embedded system voice technology other high-tech electronic means, we designed a highway early warning information system. The has some functions: accident alarm, speed warning, fast responding, traffic tips functions. Compared to traditional GPS / GPRS structure system, this more stable reliable, low...

Two-dimensional phase unwrapping (PU) is a key technique in many scientific fields. In this paper, the L1-norm-based PU implemented via novel method, which simpler than classic minimum-cost network flow (MCF) method. It proved that associated with problem can be simplified to weighted bipartite graph, and matching graph solve higher efficiency MCF Tests on simulated data real InSAR confirm proposed method has much lower computing complexity traditional

This paper is devoted to the comparative study of motion stability electrons with off-axis guiding centers in FELs a conventional and reversed guide magnetic field. Results show that trajectory divergence mainly comes from first harmonic 3-D wiggler field, can be effectively suppressed by use

Power system is an important pillar industry of national, Transmission line technology high-voltage overhead lines and difficult to safe operation. This study introduced several major transmission approach, designed a based on image processing. The uses computer recognition on-site sensors, automatically determine the abnormal power lines, alarm. Central control room staff can accurately situation field failures according images sensor information, selectively measures, command variety...

Event detection is an important step of non-intrusive load disaggregation. The accuracy event directly affects the correct rate classification identification. Aiming at shortcomings existing and feature extraction algorithms, using steady-state active power as feature, three improved algorithms are proposed: CUSUM bilateral accumulation algorithm, sliding chi-square-GOF Cepstrum analysis. algorithm compares analyzes methods. experimental results show that better than most literature results,...

Abstract The dynamic characteristic of the flood valve is an important index to ensure its safety and reliability. In this paper, CFD computational fluid dynamics (CFD) method used model simulate three-dimensional unsteady internal flow field during working process, so as obtain distribution parameters under specific conditions. modal analysis body carried out provide a calculation data support for evaluation vibration noise level operation valve.