An Intelligent Quadrotor Fault Diagnosis Method Based on Novel Deep Residual Shrinkage Network

In this paper, a fault diagnosis algorithm named improved one-dimensional deep residual shrinkage network with a wide convolutional layer (1D-WIDRSN) is proposed for quadrotor propellers with minor damage, which can effectively identify the fault classes of quadrotor under interference information, and without additional denoising procedures. In a word, that fault diagnosis algorithm can locate and diagnose the early minor faults of the quadrotor based on the flight data, so that the quadrotor can be repaired before serious faults occur, so as to prolong the service life of quadrotor. First, the sliding window method is used to expand the number of samples. Then, a novel progressive semi-soft threshold is proposed to replace the soft threshold in the deep residual shrinkage network (DRSN), so the noise of signal features can be eliminated more effectively. Finally, based on the deep residual shrinkage network, the wide convolution layer and DroupBlock method are introduced to further enhance the anti-noise and over-fitting ability of the model, thus the model can effectively extract fault features and classify faults. Experimental results show that 1D-WIDRSN applied to the minimal fault diagnosis model of quadrotor propellers can accurately identify the fault category in the interference information, and the diagnosis accuracy is over 98%.

Establishment of Effective Biomarkers for Depression Diagnosis With Fusion of Multiple Resting-State Connectivity Measures

Major depressive disorder (MDD) is a severe mental disorder and is lacking in biomarkers for clinical diagnosis. Previous studies have demonstrated that functional abnormalities of the unifying triple networks are the underlying basis of the neuropathology of depression. However, whether the functional properties of the triple network are effective biomarkers for the diagnosis of depression remains unclear. In our study, we used independent component analysis to define the triple networks, and resting-state functional connectivities (RSFCs), effective connectivities (EC) measured with dynamic causal modeling (DCM), and dynamic functional connectivity (dFC) measured with the sliding window method were applied to map the functional interactions between subcomponents of triple networks. Two-sample t-tests with p < 0.05 with Bonferroni correction were used to identify the significant differences between healthy controls (HCs) and MDD. Compared with HCs, the MDD showed significantly increased intrinsic FC between the left central executive network (CEN) and salience network (SAL), increased EC from the right CEN to left CEN, decreased EC from the right CEN to the default mode network (DMN), and decreased dFC between the right CEN and SAL, DMN. Moreover, by fusion of the changed RSFC, EC, and dFC as features, support vector classification could effectively distinguish the MDD from HCs. Our results demonstrated that fusion of the multiple functional connectivities measures of the triple networks is an effective way to reveal functional disruptions for MDD, which may facilitate establishing the clinical diagnosis biomarkers for depression.

Simulation and Detection of Small Drones/Suspicious UAVs in Drone Grid

Today’s technology is evolving towards autonomous systems and the demand in autonomous drones, cars, robots, etc. has increased drastically in the past years. This project presents a solution for autonomous real-time visual detection and tracking of hostile drones by moving cameras equipped on surveillance drones. The algorithm developed in this project, based on state-of-art machine learning and computer vision methods, succeeds at autonomously detecting and tracking a single drone by moving a camera and can run at real-time. The project can be divided into two main parts: the detection and the tracking. The detection is based on the YOLOv3 (You Only Look Once v3) algorithm and a sliding window method. The tracking is based on the GOTURN (Generic Object Tracking Using Regression Networks) algorithm, which allows the tracking of generic objects at high speed. In order to allow autonomous tracking and enhance the accuracy, a combination of GOTURN and tracking by detection using YOLOv3 was developed.

Effect of jet lag on brain white matter functional connectivity

Background A long-haul flight across more than five time zones may produce a circadian rhythm sleep disorder known as jet lag. Little is known about the effect of jet lag on white matter (WM) functional connectivity (FC). Objective The present study is to investigate changes in WM FC in subjects due to recovery from jet lag after flying across six time zones. Methods Here, resting-state functional magnetic resonance imaging was performed in 23 participants within 24 hours of flying and again 50 days later. Gray matter (GM) and WM networks were identified by k-means clustering. WM FC and functional covariance connectivity (FCC) were analyzed. Next, a sliding window method was used to establish dynamic WM FC. WM static and dynamic FC and FCC were compared between when participants had initially completed their journey and 50 days later. Emotion was assessed using the Positive and Negative Affect Schedule and the State Anxiety Inventory. Results All participants were confirmed to have jet lag symptoms by the Columbian Jet Lag Scale. The static FC strengthes of cingulate network (WM7)- sensorimotor network and ventral frontal network- visual network were lower after the long-haul flight compared with recovery. Corresponding results were obtained for the dynamic FC analysis. The analysis of FCC revealed weakened connections between the WM7 and several other brain networks, especially the precentral/postcentral network. Moreover, a negative correlation was found between emotion scores and the FC between the WM7 and sensorimotor related regions. Conclusions The results of this study provide further evidence for the existence of WM networks and show that jet lag is associated with alterations in static and dynamic WM FC and FCC, especially in sensorimotor networks. Jet lag is a complex problem that not only is related to sleep rhythm but also influences emotion.

Algorithm for error-free determination of the variance of all contiguous subsequences and fixed-length contiguous subsequences for a sequence of industrial measurement data

The article presents an algorithm for fast and error-free determination of statistics such as the arithmetic mean and variance of all contiguous subsequences and fixed-length contiguous subsequences for a sequence of industrial measurement data. Additionally, it shows that both floating-point and integer representation can be used to perform this kind of statistical calculations. The author proves a theorem on the number of bits of precision that an arithmetic type must have to guarantee error-free determination of the arithmetic mean and variance. The article also presents the extension of Welford’s formula for determining variance for the sliding window method—determining the variance of fixed-length contiguous subsequences. The section dedicated to implementation tests shows the running times of individual algorithms depending on the arithmetic type used. The research shows that the use of integers in calculations makes the determination of the aforementioned statistics much faster.

Thinning Evaluation of Steel Plates for Weathering Tests Based on Convolutional Neural Networks

Weathering tests using monitored steel plates are a widely applied method for evaluating the atmospheric corrosion rate in Japan. To calculate the regional corrosion rate, the corrosion layer on the surface of the steel plate needs to be removed to determine the thinning. However, the process of removing the corrosion layer is time and labor consuming. To tackle this issue, this study proposed an image recognition method based on convolutional neural networks (CNNs) to evaluate the thinning of weathering test samples. To this end, the existing data collected from the weathering tests were reused to generate a dataset named “Corrosion-Fukui” that consisted of 77 raw images labeled with their numerical extent of thinning. To generate more samples for training, a criteria based on thinning extent that classified the raw images into six corrosion levels were defined to implement cropping operation on the raw images with uniform corrosion morphology. Correspondingly, the raw images of the corroded samples with uniform corrosion morphology were chosen as “training” and “validation samples” to be cropped into small pieces labeled with the corrosion levels, whereas other raw images with nonuniform corrosion morphology were chosen as “test samples.” The performance of the proposed baseline model VGGGAP as well as three state-of-art CNN models was cross-validated on the augmented dataset and tested upon the test images using a sliding window method. The evaluation results of the 17 testing samples indicated that the corrosion thinning of the weathering test samples can be directly evaluated more efficiently from digital images using CNNs than using conventional corrosion removal methods.

BFRVSR: A Bidirectional Frame Recurrent Method for Video Super-Resolution

Video super-resolution is a challenging task. One possible solution, called the sliding window method, tries to divide the generation of high-resolution video sequences into independent subtasks. Another popular method, named the recurrent algorithm, utilizes the generated high-resolution images of previous frames to generate the high-resolution image. However, both methods have some unavoidable disadvantages. The former method usually leads to bad temporal consistency and has higher computational cost, while the latter method cannot always make full use of information contained by optical flow or any other calculated features. Thus, more investigations need to be done to explore the balance between these two methods. In this work, a bidirectional frame recurrent video super-resolution method is proposed. To be specific, reverse training is proposed that also utilizes a generated high-resolution frame to help estimate the high-resolution version of the former frame. The bidirectional recurrent method guarantees temporal consistency and also makes full use of the adjacent information due to the bidirectional training operation, while the computational cost is acceptable. Experimental results demonstrate that the bidirectional super-resolution framework gives remarkable performance and it solves time-related problems.