Sleep is an essential integrant in everyone's daily life. Thereby, it important but challenging problem to construct a reliable and stable system, that can monitor user's sleep quality automatically. In this brief, we combine complex network deep learning propose novel Graph-Temporal fused dual-input Convolutional Neural Network (CNN) method detect stages by using the Sleep-EDF database. Firstly, segment each single-channel EEG signal into non-overlapping 30s epochs set up network. For that,...

Abstract In this study, we aimed to address the primary challenges encountered in industrial integrated circuit (IC) surface defect detection, particularly focusing on imbalance information density arising from difficulties data sample collection. To end, have developed a new hybrid architecture model for IC detection (SDDM), based ResNet and Vision Transformer (ViT). The core innovation of SDDM lies integration concepts image dataset density, effectively identifying processing areas high...

The random fluctuation of wind leads to the instability power, particularly power intermittency is a critical event in case grid connected plants, leading severe consequences like low system reliability, high reserve capacity and operational costs. This paper proposes novel speed prediction model based on ramp (WSR) residual distribution. Firstly, variational mode decomposition (VMD) used decompose original series extract different characteristics, several sub-sequences are obtained. Then,...

Underwater thrusters, vital components in various underwater vehicles, have been extensively studied for fault identification and classification. However, the automatic unsupervised assessment of levels remains largely unexplored. This article presents a novel approach integrating physical information into data-driven architecture training process, enabling automated evaluation. The process begins with constructing model thruster estimating its low-fidelity current based on vehicle's...

The navigation and localization of Autonomous Underwater Vehicle (AUV) face many challenges. In surface missions, AUV typically relies only on Global Positioning System (GPS) to perform navigation. However, the GPS data output frequency is low, usually 1 Hz. Meanwhile, system susceptible interference from measurement outliers. For underwater without assistance additional absolute positioning measurements, unknown errors introduced by modeling process state estimation will affect accuracy....

Ultra-short term wind speed forecast for farm is of great significance to the real-time scheduling power system. In this paper, NWP (Numerical Weather Prediction) time series and measured were decomposed into different bands by wavelet multi-resolution analysis. Pearson product-moment correlation coefficient was used verify correction premise. Then linear method correct low frequency stationary speed. To test approach, data from Yilan Heilongjiang province used. The results show that when a...

An efficient design methodology and a systematic approach for the implementation of multiplication squaring functions unsigned large integers, using small-size embedded multipliers are presented. A general architecture multiplier squarer is proposed set equations derived to aid in realisation. The inputs split into several segments leading an utilisation reduced number required addition operations. Various benchmarks were tested different ranging from 2 5 targeting Xilinx Spartan-3 FPGAs....

Wind power is one of the most promising means generation. But time-varying wind speed fundamental problem for generation control system. Therefore, ac ...

This article presents an effective cruise speed estimation strategy for low-cost autonomous underwater vehicles under the impact of complex ocean currents and absence critical navigation sensors. The is based on motor feedback information, including current propeller speed. requires a rough minor adjustments to ensure that estimated valuable. In this article, multiple fuzzy logic applied generate mapping between deviation, speed, deviation. Afterward, recursive least square introduced...

Based on data-driven and mixed models, this study proposes a fault detection method for autonomous underwater vehicle (AUV) rudder systems. The proposed can effectively detect faults in the absence of angle feedback from rudder. Considering parameter uncertainty AUV motion model resulting dynamics analysis method, we present identification based recurrent neural network (RNN). Prior to identification, singular value decomposition (SVD) was chosen denoise original sensor data as pretreatment...

Under the high dynamic conditions, Global Navigation Satellite System (GNSS) signals produce great Doppler frequency shifts, which hinders fast acquisition of signals. Inertial (INS)-aided can improve performance, whereas accuracy shift and code phase estimation are mainly determined by INS precision. The relation between error has been derived, while not deduced. In this paper, in order to theoretically analyze effects errors on performance estimations, connections them re-deduced....

Aiming to improve survey accuracy of Measurement While Drilling (MWD) based on Fiber Optic Gyroscopes (FOGs) in the long period, external aiding sources are fused into inertial navigation by Kalman filter (KF) method. The KF method needs model sensors' noise as system model. is modeled white Gaussian conventionally. However, because vibration while drilling, gyros isn't any more. Moreover, an incorrect will degrade KF. This paper developed a new approach for modeling basis dynamic Allan...

In the future, smart intelligent ammunition will be widely applied in military field. Small volume microelectromechanical system inertial measurement units (MIMUs) have become mainstream solution for a navigation system; however, accuracy of IMU is main factor limiting strikes. To improve MIMU, various integrated methods been proposed, example, integration global satellite (GNSS) and magnetometer. this study, compound (CPNS) designed to MIMU. The CPNS consists an oblique single-axis fiber...

There are a large number of cloud-covered areas in most unmanned aerial vehicle images and lead to the loss information image affect post procession such as fusion target identification. Finding cloud-occluded area an is key step processing. Based on differences color texture characteristics between cloud ground, detection algorithm for proposed. Simulation results show that proposed better than classical algorithms accuracy rate, false-positive kappa coefficient.

Accurate visual re-localization is very critical to many artificial intelligence applications, such as augmented reality, virtual robotics and autonomous driving. To accomplish this task, we propose an integrated method called RLOCS by combining image retrieval, semantic consistency geometry verification achieve accurate estimations. The localization pipeline designed a coarse-to-fine paradigm. In the retrieval part, cascade architecture of ResNet101-GeM-ArcFace employ DBSCAN followed...