Intelligent fault diagnosis methods based on signal analysis have been widely used for bearing fault diagnosis. These methods use a pre-determined transformation (such as empirical mode ...decomposition, fast Fourier transform, discrete wavelet transform) to convert time-series signals into frequency domain signals, the performance of dignostic system is significantly rely on the extracted features. However, extracting signal characteristic is fairly time consuming and depends on specialized signal processing knowledge. Although some studies have developed highly accurate algorithms, the diagnostic results rely heavily on large data sets and unreliable human analysis. This study proposes an automatic feature learning neural network that utilizes raw vibration signals as inputs, and uses two convolutional neural networks with different kernel sizes to automatically extract different frequency signal characteristics from raw data. Then long short-term memory was used to identify the fault type according to learned features. The data is down-sampled before inputting into the network, greatly reducing the number of parameters. The experiment shows that the proposed method can not only achieve 98.46% average accuracy, exceeding some state-of-the-art intelligent algorithms based on prior knowledge and having better performance in noisy environments.
This study is concerned with the leader-follower formation control of non-holonomic mobile robots without communication. A pan-controlled camera is the sole sensor used by the follower to observe the ...leader. A new vision-based formation system without range states is proposed, which eliminates the need of inter-robot range estimation. An adaptive formation controller and an adaptive camera controller are designed in the presence of unknown leader's velocities and vision-related parameters. A parameter projection algorithm is integrated into the controllers to bound the control inputs. The camera controller ensures the stable observation of the leader's features. Thus the camera constantly provides visual measurements for the formation controller which guarantees the formation maintenance. Simulation and experimental results verify the effectiveness of the proposed active vision-based formation control approach.
SUMMARY
We propose a new array covariance matrix analysis method, named ‘maximum covariance direction method’ (MCD method), to detect and locate unconventional seismic sources of weak signals without ...clear onsets. The MCD method builds a normalized-covariance matrix of time-shifted seismic waveforms recorded in a seismic array and determines the existence of source based on the consistency of the maximum covariance direction with the theoretical prediction. Synthetic tests demonstrate effectiveness of the MCD method in detecting one and multiple isolated sources with low signal-to-noise ratios. As a data application, we study 1-hr long-period tremors (LPTs) around Aso Volcano of Japan in 2014 November 24. A total of 26 LPTs are detected near the Naka-dake first crater of Aso Volcano, with the uncertainties of source location of about 7 km. Using the recorded background noise at the seismic stations, we show that the MCD method can detect LPTs even when the LPT signals are buried in the background noise and become indiscernible in the seismic data. Unlike traditional methods that employ the coherent features of seismic signals for source detection, the MCD method places emphases on both the coherence of seismic signals and consistency of the direction of the coherent signals from a potential source location. The synthetic tests and data application indicate that the MCD method provides a good alternative to other traditional methods for detecting and locating unconventional seismic sources, with a major improvement of avoiding source misidentification in the presence of strong incoherent signals.
Due to the limited clinical utility of individual biomarkers, there is growing recognition of the need for combining multiple biomarkers as a panel to improve the accuracy and efficacy of disease ...diagnosis and prognosis. The conventional method to detect multiple analyte species is to construct a sensor array, which consists of an array of individual selective probes for different species. In this work, by using cancer biomarker matrix metalloproteinases (MMPs) and a disintegrin and metalloproteinases (ADAMs) as model analytes and functionalized nanographene oxide (nGO) as a sensing element, we developed a multiplexing fluorescence sensor in a nonarray format for simultaneous measurement of the activities of multiple proteases. The constructed nGO-based biosensor was rapid, sensitive, and selective and was also utilized for the successful profiling of ADAMs/MMPs in simulated serum samples. Furthermore, we showed that joint entropy and programming could be utilized to guide experiment design, especially in terms of the selection of a subset of proteases from the entire MMPs/ADAMs family as an appropriate biomarker panel. Our developed nGO-based multiplex sensing platform should find useful application in early cancer detection and diagnosis.
Here, we present a multi-modal deep generative model, the single-cell Multi-View Profiler (scMVP), which is designed for handling sequencing data that simultaneously measure gene expression and ...chromatin accessibility in the same cell, including SNARE-seq, sci-CAR, Paired-seq, SHARE-seq, and Multiome from 10X Genomics. scMVP generates common latent representations for dimensionality reduction, cell clustering, and developmental trajectory inference and generates separate imputations for differential analysis and cis-regulatory element identification. scMVP can help mitigate data sparsity issues with imputation and accurately identify cell groups for different joint profiling techniques with common latent embedding, and we demonstrate its advantages on several realistic datasets.
Visual object tracking is an important technology in camera-based sensor networks, which has a wide range of practicability in auto-drive systems. A transformer is a deep learning model that adopts ...the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It causes such transformer-based applications to be exposed to security threats. In this work, the security of the transformer model was investigated with an important component of autonomous driving, i.e., visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, and thus, adversarial attacks were implemented as the security threats to conduct the investigation. First, adversarial examples were generated on top of video sequences to degrade the tracking performance, and the frame-by-frame temporal motion was taken into consideration when generating perturbations over the depicted tracking results. Then, the influence of perturbations on performance was sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrated that the executed adversarial examples were effective on the performance drops of the transformer-based visual tracking. White-box attacks showed the highest effectiveness, where the attack success rates exceeded 90% against transformer-based trackers.
Crustin is an antimicrobial peptide (AMP) that plays a key role in the innate immunity of crustaceans. This study cloned a new crustin from Pacific white shrimp Litopenaeus vannamei, which we ...designated as LvCrustinB, using rapid amplification of cDNA ends (RACE). The full-length cDNA of LvCrustinB is 751 bp with an open reading frame (ORF) of 591 bp encoding a peptide of 196 amino acids that includes a putative signal sequence. LvCrustinB is a type II crustin that has a glycine-rich region and a single whey acidic protein domain (WAP) domain. The mRNA transcript of LvCrustinB was detected in all examined tissues and was found to be most abundantly expressed in the epithelium and muscle. The expression of LvCrustinB in hemocytes was significantly upregulated after L. vannamei was challenged with LPS, Vibrio parahaemolyticus, and white spot syndrome virus (WSSV). When LvCrustinB was knocked down with RNAi, the mortality rate of L. vannamei significantly increased after V. parahaemolyticus or WSSV infection. Recombinant LvCrustinB was produced using Pichia pastoris GS115 and was shown to bind to 2 g-positive bacteria (Staphylococcus aureus and Bacillus subtilis) and 2 g-negative bacteria (Escherichia coli and V. parahaemolyticus) via polysaccharides, which included PGN, LTA, and LPS. In vivo, the recombinant LvCrustinB remarkably protected L. vannamei from V. parahaemolyticus infection. These results suggest that LvCrustinB plays an important role in innate immunity and may be potentially utilized as antibacterial agents in shrimp.
•A new crustin gene (LvCrustinB) from pacific white shrimp Litopenaeus vannamei.•LvCrustinB is ubiquitously distributedand its expression is up-regulated by V. parahaemolyticus or WSSV infection.•LvCrustinB directly bind to polysaccharides, which included PGN, LTA, and LPS.•LvCrustinB is involved in antibacterial immune defense against V. parahaemolyticus in vivo.
The H7N9 avian influenza virus (AIV) that emerged in China have caused five waves of human infection. Further human cases have been successfully prevented since September 2017 through the use of an ...H7N9 vaccine in poultry. However, the H7N9 AIV has not been eradicated from poultry in China, and its evolution remains largely unexplored. In this study, we isolated 19 H7N9 AIVs during surveillance and diagnosis from February 2018 to December 2019, and genetic analysis showed that these viruses have formed two different genotypes. Animal studies indicated that the H7N9 viruses are highly lethal to chicken, cause mild infection in ducks, but have distinct pathotypes in mice. The viruses bound to avian-type receptors with high affinity, but gradually lost their ability to bind to human-type receptors. Importantly, we found that H7N9 AIVs isolated in 2019 were antigenically different from the H7N9 vaccine strain that was used for H7N9 influenza control in poultry, and that replication of these viruses cannot, therefore, be completely prevented in vaccinated chickens. We further revealed that two amino acid mutations at positions 135 and 160 in the HA protein added two glycosylation sites and facilitated the escape of the H7N9 viruses from the vaccine-induced immunity. Our study provides important insights into H7N9 virus evolution and control.
The effect of axial yarns on progressive bending damage of braided composite tubes is studied in this paper. Four specimens with different number and distribution of axial yarns were experimentally ...tested by quasi-static three-point bending. At the same time, infrared thermography was used to observe the damage in-situ. Combined with the cross-section morphology of Ultra-Depth 3D Microscope, the damage evolution and distribution characteristics of braided tubes were identified. It is found that axial yarns enhance the mechanical properties of braided composite tube. The detected changes of infrared maximum temperature have a good correlation with the damage initiation and failure mechanism of the specimen. The abrupt changes of the maximum temperature indicate the occurrence of local fiber breakage, especially the axial yarn breakage. If there are axial yarns on the compression side of the tube, the maximum temperature increases by 0.5 °C in the linear elastic stage, and two initial damages of debonding and fiber breakage will occur. The debonding started at the interface of the axial yarn. The axial yarns increased fiber crimp, resulting in obvious wavy delamination between layers of the specimen, and the axial damage range was expanded. In addition, the mixed structure with axial yarns only on the compression side can inhibit the damage from spreading down the braided tube wall.
•The progressive bending damage of triaxial braided tube was studied.•The abrupt change of infrared maximum temperature indicates local fiber breakage.•The mixed structure with axial yarns only in the upper half can inhibit damage spreading downward.