Epileptic Seizure Detection Based on Time-Frequency Images of EEG Signals Using Gaussian Mixture Model and Gray Level Co-Occurrence Matrix Features.

The electroencephalogram (EEG) signal analysis is a valuable tool in the evaluation of neurological disorders, which is commonly used for the diagnosis of epileptic seizures. This paper presents a novel automatic EEG signal classification method for epileptic seizure detection. The proposed method first employs a continuous wavelet transform (CWT) method for obtaining the time-frequency images (TFI) of EEG signals.

Monocular Visual-Inertial SLAM:Continuous Preintegration and Reliable Initialization.

In this paper, we propose a new visual-inertial Simultaneous Localization and Mapping (SLAM) algorithm. With the tightly coupled sensor fusion of a global shutter monocular camera and a low-cost Inertial Measurement Unit (IMU), this algorithm is able to achieve robust and real-time estimates of the sensor poses in unknown environment. To address the real-time visual-inertial fusion problem, we present a parallel framework with a novel IMU initialization method.

Deep kernel learning method for SAR image target recognition.

With the development of deep learning, research on image target recognition has made great progress in recent years. Remote sensing detection urgently requires target recognition for military, geographic, and other scientific research. This paper aims to solve the synthetic aperture radar image target recognition problem by combining deep and kernel learning.

An integrated guidance and control approach in three-dimensional space for hypersonic missile constrained by impact angles.

A new robust three-dimensional integrated guidance and control (3D-IGC) approach is investigated for sliding-to-turn (STT) hypersonic missile, which encounters high uncertainties and strict impact angle constraints. First, a nonlinear state-space model with more generality is established facing to the design of 3D-IGC law. With regard to the as-built nonlinear system, a robust dynamic inversion control (RDIC) approach is proposed to overcome the robustness deficiency of traditional DIC, and then it is applied to construct the basic 3D-IGC law combining with backstepping method.

A novel extended state observer.

A novel extended state observer, which feeds back the output estimation error via both nonlinear and switching terms, is put forward for the first time in this paper. No longer neglecting the lumped uncertainty׳s first time derivative, the problem of disturbance observer design is transformed into the problem of state observer design in the presence of external disturbance. The switching term of the output estimation error is employed to counteract the adverse effect of external disturbance.

Optimal Parameter Design of Coarse Alignment for Fiber Optic Gyro Inertial Navigation System.

Two different coarse alignment algorithms for Fiber Optic Gyro (FOG) Inertial Navigation System (INS) based on inertial reference frame are discussed in this paper. Both of them are based on gravity vector integration, therefore, the performance of these algorithms is determined by integration time. In previous works, integration time is selected by experience.

Guidance law against maneuvering targets with intercept angle constraint.

This study explores the guidance law against maneuvering targets with the intercept angle constraint. The limitation of the traditional guidance law, which simply treats the unknown target acceleration as zero, has been analyzed. To reduce this limitation, a linear extended state observer is constructed to estimate the acceleration of the maneuvering target to enhance the tracking performance of the desired intercept angle.