BMSCs-laden mechanically reinforced bioactive sodium alginate composite hydrogel microspheres for minimally invasive bone repair.

Minimally invasive, efficient, and satisfactory treatment for irregular and lacunar bone defects is still a challenge. Alginate hydrogels serve as promising stem cell (SC) delivery systems for bone regeneration but are limited by low cellular viability, poor osteogenic differentiation, and insufficient mechanical support. Herein, we developed a BMSCs-laden mechanically reinforced bioactive sodium alginate composite hydrogel microspheres (BCHMs) system via a microfluidic method that possesses 1) a uniform size and good injectability to meet clinical bone defects with complex shapes, 2) high cellular viability maintenance and further osteogenic induction capacity, and 3) improved mechanical properties. As the main matrix, the sodium alginate hydrogel maintains the high viability of encapsulated BMSCs and efficient substance exchange. Enhanced mechanical properties and osteogenic differentiation of the BCHMs in vitro were observed with xonotlite (Ca6Si6O17(OH)2, CSH) nanowires incorporated. Furthermore, BCHMs with 12.5 % CSH were injected into rat femoral bone defects, and satisfactory in situ regeneration outcomes were observed. Overall, it is believed that BCHMs expand the application of polysaccharide science and provide a promising injectable bone substitute for minimally invasive bone repair.

Automating the Human Action of First-Trimester Biometry Measurement from Real-World Freehand Ultrasound.

OBJECTIVE: Automated medical image analysis solutions should closely mimic complete human actions to be useful in clinical practice. However, more often an automated image analysis solution represents only part of a human task, which restricts its practical utility. In the case of ultrasound-based fetal biometry, an automated solution should ideally recognize key fetal structures in freehand video guidance, select a standard plane from a video stream and perform biometry. A complete automated solution should automate all three subactions. METHODS: In this article, we consider how to automate the complete human action of first-trimester biometry measurement from real-world freehand ultrasound. In the proposed hybrid convolutional neural network (CNN) architecture design, a classification regression-based guidance model detects and tracks fetal anatomical structures (using visual cues) in the ultrasound video. Several high-quality standard planes that contain the mid-sagittal view of the fetus are sampled at multiple time stamps (using a custom-designed confident-frame detector) based on the estimated probability values associated with predicted anatomical structures that define the biometry plane. Automated semantic segmentation is performed on the selected frames to extract fetal anatomical landmarks. A crown-rump length (CRL) estimate is calculated as the mean CRL from these multiple frames. RESULTS: Our fully automated method has a high correlation with clinical expert CRL measurement (Pearson's p = 0.92, R-squared [R2] = 0.84) and a low mean absolute error of 0.834 (weeks) for fetal age estimation on a test data set of 42 videos. CONCLUSION: A novel algorithm for standard plane detection employs a quality detection mechanism defined by clinical standards, ensuring precise biometric measurements.

A xonotlite nanofiber bioactive 3D-printed hydrogel scaffold based on osteo-/angiogenesis and osteoimmune microenvironment remodeling accelerates vascularized bone regeneration.

BACKGROUND: Coordination between osteo-/angiogenesis and the osteoimmune microenvironment is essential for effective bone repair with biomaterials. As a highly personalized and precise biomaterial suitable for repairing complex bone defects in clinical practice, it is essential to endow 3D-printed scaffold the above key capabilities. RESULTS: Herein, by introducing xonotlite nanofiber (Ca6(Si6O17) (OH)2, CS) into the 3D-printed silk fibroin/gelatin basal scaffold, a novel bone repair system named SGC was fabricated. It was noted that the incorporation of CS could greatly enhance the chemical and mechanical properties of the scaffold to match the needs of bone regeneration. Besides, benefiting from the addition of CS, SGC scaffolds could accelerate osteo-/angiogenic differentiation of bone mesenchymal stem cells (BMSCs) and meanwhile reprogram macrophages to establish a favorable osteoimmune microenvironment. In vivo experiments further demonstrated that SGC scaffolds could efficiently stimulate bone repair and create a regeneration-friendly osteoimmune microenvironment. Mechanistically, we discovered that SGC scaffolds may achieve immune reprogramming in macrophages through a decrease in the expression of Smad6 and Smad7, both of which participate in the transforming growth factor-ß (TGF-ß) signaling pathway. CONCLUSION: Overall, this study demonstrated the clinical potential of the SGC scaffold due to its favorable pro-osteo-/angiogenic and osteoimmunomodulatory properties. In addition, it is a promising strategy to develop novel bone repair biomaterials by taking osteoinduction and osteoimmune microenvironment remodeling functions into account.

A multifunctional quercetin/polycaprolactone electrospun fibrous membrane for periodontal bone regeneration.

Image 1.

Prior skeleton based online deep reinforcement learning for coronary artery centerline extraction.

Coronary centerline extraction is an essential technique for X-ray coronary angiography (XCA) image analysis, which provides qualitative and quantitative guidance for percutaneous coronary intervention (PCI). In this paper, an online deep reinforcement learning method for coronary centerline extraction is proposed based on the prior vascular skeleton. Firstly, with XCA image preprocessing (foreground extraction and vessel segmentation) results, the improved ZhangSuen image thinning algorithm is used to rapidly extract the preliminary vascular skeleton network. On this basis, according to the spatial-temporal and morphological continuity of the angiography image sequence, the connectivity of different branches is determined using k-means clustering, and the vessel segments are then grouped, screened, and reconnected to obtain the aorta and its major branches. Finally, using the previous results as prior information, an online Deep Q-Network (DQN) reinforcement learning method is proposed to optimize each branch simultaneously. It comprehensively considers grayscale intensity and eigenvector continuity to achieve the combination of data-driven and model-driven without pre-training. Experimental results on clinical images and the third-party dataset demonstrate that the proposed method can accurately extract, restructure, and optimize the centerline of XCA images with a higher overall accuracy than the existing state-of-the-art methods.

Kinsenoside alleviates oxidative stress-induced blood-brain barrier dysfunction via promoting Nrf2/HO-1 pathway in ischemic stroke.

An ischemic stroke usually causes blood-brain barrier (BBB) damage and excessive oxidative stress (OS) levels. Kinsenoside (KD), a major effective compound extracted in Chinese herbal medicine Anoectochilus roxburghii (Orchidaceae), has anti-OS effects. The present study focused on exploring KD's protection against OS-mediated cerebral endothelial cell damage and BBB damage within the mouse model. Intracerebroventricular administration of KD upon reperfusion after 1 h ischemia decreased infarct volumes, neurological deficit, brain edema, neuronal loss, and apoptosis 72 h post-ischemic stroke. KD improved BBB structure and function, as evidenced by a lower 18F-fluorodeoxyglucose pass rate of the BBB and upregulation of tight junction (TJ) proteins such as occludin, claudin-5, and zonula occludens-1 (ZO-1). KD protected bEnd.3 endothelial cells from oxygen and glucose deprivation/reoxygenation (OGD/R) injury in an in-vitro study. Meanwhile, OGD/R reduced transepithelial electronic resistance, whereas KD significantly increased TJ protein levels. Furthermore, based on in-vivo and in-vitro research, KD alleviated OS in endothelial cells, which is related to nuclear factor, erythroid 2 like 2 (Nrf2) nuclear translocation as well as Nrf2/haem oxygenase 1 signaling protein stimulation. Our findings demonstrated that KD might serve as a potential compound for treating ischemic stroke involving antioxidant mechanisms.

A Machine Learning Method for Automated Description and Workflow Analysis of First Trimester Ultrasound Scans.

Obstetric ultrasound assessment of fetal anatomy in the first trimester of pregnancy is one of the less explored fields in obstetric sonography because of the paucity of guidelines on anatomical screening and availability of data. This paper, for the first time, examines imaging proficiency and practices of first trimester ultrasound scanning through analysis of full-length ultrasound video scans. Findings from this study provide insights to inform the development of more effective user-machine interfaces, of targeted assistive technologies, as well as improvements in workflow protocols for first trimester scanning. Specifically, this paper presents an automated framework to model operator clinical workflow from full-length routine first-trimester fetal ultrasound scan videos. The 2D+t convolutional neural network-based architecture proposed for video annotation incorporates transfer learning and spatio-temporal (2D+t) modelling to automatically partition an ultrasound video into semantically meaningful temporal segments based on the fetal anatomy detected in the video. The model results in a cross-validation A1 accuracy of 96.10% , F1=0.95 , precision =0.94 and recall =0.95 . Automated semantic partitioning of unlabelled video scans (n=250) achieves a high correlation with expert annotations ( ρ = 0.95, p=0.06 ). Clinical workflow patterns, operator skill and its variability can be derived from the resulting representation using the detected anatomy labels, order, and distribution. It is shown that nuchal translucency (NT) is the toughest standard plane to acquire and most operators struggle to localize high-quality frames. Furthermore, it is found that newly qualified operators spend 25.56% more time on key biometry tasks than experienced operators.

Enhancing the osteogenic differentiation of aligned electrospun poly(L-lactic acid) nanofiber scaffolds by incorporation of bioactive calcium silicate nanowires.

Bone defects cause serious psychological and economic burden to patients. Artificially bone repairing materials bring hope to the treatment of bone defects. Electrospun technique has attracted great attention since it can fabricate fibers from nano- to micro- scale continuously. Scaffolds fabricated by electrospun can mimic the structure of extracellular matrix which is beneficial to cell adhesion and migration. Researches have showed that bioactive ions (such as silicon and calcium ions) can promote bone regeneration. In addition, physical cues can affect cellular behavior such as cell adhesion and differentiation. In this study, two kinds of calcium silicate - adopted poly (L-lactic acid) (CS-PLLA) electrospun scaffolds with random/aligned structures were prepared by electrospun to promote bone regeneration. The integration of CS nanowires improved the biological property of PLLA electrospun scaffolds. Furthermore, in vitro results indicated that aligned 1 wt% CS adopted PLLA (PCA1) electrospun scaffolds with better physical properties and facilitated cell adhesion, improved alkaline phosphate (ALP) activity and the expression of osteogenic genes (Osteopontin (OPN), Collagen type 1 (Col-1) and Bone morphogenetic protein-2 (BMP-2)) compared with random 1 wt% CS adopted PLLA (PCR1) electrospun scaffolds. In conclusion, the prepared PCA1 electrospun scaffolds might be a potential candidate for bone regeneration in defect areas.

Phosphotungstate Acid Doped Polyanilines Nanorods for in situ NIR-II Photothermal Therapy of Orthotopic Hepatocellular Carcinoma in Rabbit.

Introduction: Second near-infrared photothermal therapy (NIR-II PTT) has become a promising strategy for treating cancer in terms of safety and potency. However, the application of NIR-II PTT was limited in the treatment of deep-buried solid tumors due to the low dose of NIR-II absorption nanomaterials and the inadequate laser energy in the deep tumor. Methods: Herein, the authors report the engineering of NIR-II absorbing polyaniline nanorods, termed HPW@PANI Nanorods, for in situ NIR-II PTT based on optical fibers transmission of laser power and transarterial infusion for the treatment of orthotopic hepatocellular carcinoma in the rabbit. HPW@PANI Nanorods were prepared via chemical oxidant polymerization of aniline under phosphotungstic acid, which exhibited effective NIR-II absorption for hyperthermia ablation cells. Results: HPW@PANI Nanorods were fast and efficiently deposited into primary orthotopic transplantation VX2 tumor in rabbits via transarterial infusion. Furthermore, an optical fiber was interventionally inserted into the primary VX2 tumor to transmit 1064nm laser energy for in situ NIR-II PTT, which could ablate primary tumor, inhibit distant tumor, and suppress peritoneal metastasis. Conclusion: This study provides new insights into the application of in situ NIR-II PTT based on optical fibers transmission of laser power and transarterial injection of NIR-II absorption nanomaterials to treat deep-buried tumors.

Long-range high-speed laser imaging based on VCSEL array and MPPC array.

Flash LiDAR is a photoelectric system that can acquire a 3D image by emitting a diffuse pulsed laser beam, and hence is suitable for both autopilot and spacecraft flight control. Achieving long-range and high-speed, especially in outdoor applications with strong solar background illumination, are challenging requirements. In this paper, a set of laser imaging prototype based on 2×6 VCSEL array and 32×32 MPPC array image sensor is developed, the range calibration is completed, and relevant experimental research is carried out. The frame rate of the system can reach 10kHz, the detection probability of 120m range can reach 86.23%, and the maximum walk error is about 0.6m under different reflectivity. The 3D imaging of the vehicle can be realized at about 70m, the horizontal spatial resolution is less than 5cm, and the ranging precision after ten shots average is within 10cm by calculating the centroid of a histogram. The detection probability can be improved by using the time-gating method. After multiple measurements, a 120m "laser imaging through window" can be realized in sunlight. This LiDAR system has the advantages of small volume, light weight and fast detection speed.

Coaxially Fabricated Dual-Drug Loading Electrospinning Fibrous Mat with Programmed Releasing Behavior to Boost Vascularized Bone Regeneration.

In clinical treatment, the bone regeneration of critical-size defects is desiderated to be solved, and the regeneration of large bone segment defects depends on early vascularization. Therefore, overcoming insufficient vascularization in artificial bone grafts may be a promising strategy for critical-size bone regeneration. Herein, a novel dual-drug programmed releasing electrospinning fibrous mat (EFM) with a deferoxamine (DFO)-loaded shell layer and a dexamethasone (DEX)-loaded core layer is fabricated using coaxial electrospinning technology, considering the temporal sequence of vascularization and bone repair. DFO acts as an angiogenesis promoter and DEX is used as an osteogenesis inducer. The results demonstrate that the early and rapid release of DFO promotes angiogenesis in human umbilical vascular endothelial cells and the sustained release of DEX enhances the osteogenic differentiation of rat bone mesenchymal stem cells. DFO and DEX exert synergetic effects on osteogenic differentiation via the Wnt/ß-catenin signaling pathway, and the dual-drug programmed releasing EFM acquired perfect vascularized bone regeneration ability in a rat calvarial defect model. Overall, the study suggests a low-cost strategy to enhance vascularized bone regeneration by adjusting the behavior of angiogenesis and osteogenesis in time dimension.

Quercetin-Coating Promotes Osteogenic Differentiation, Osseointegration and Anti-Inflammatory Properties of Nano-Topographic Modificated 3D-Printed Ti6Al4V Implant.

The capabilities of osseointegration and anti-inflammatory properties are of equal significance to the bio-inert titanium implant surface. Quercetin has proved its capacities of activating anti-inflammation through macrophage modulation and promoting osteogenic differentiation. Herein, we fabricated quercetin-coating on nano-topographic modificated 3D-printed Ti6Al4V implant surface. Subsequently the biological cells responses in vitro, anti-inflammatory and osseointegration performance in vivo were evaluated. In vitro studies indicated that quercetin-coating can enhance the adhesion and osteogenic differentiation of rBMSCs, while modulating the polarization of macrophages from M1 to M2 phase and improving the anti-inflammatory and vascular gene expression. Moreover, quercetin-loaded implants reduced the level of peri-implant inflammation and ameliorated new bone formation and rapid osseoinegration in vivo. Quercetin-coating might provide a feasible and favorable scheme for endowing 3D-printed titanium alloy implant surface with enhanced the rapid osseointegration and anti-inflammatory properties.

Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound.

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pair sampling in a contrastive learning manner. The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning. We empirically investigate the effect of inclusion of anatomy information with coarse- and fine-grained granularity, for contrastive learning and find that learning with fine-grained anatomy information which preserves intra-class difference is more effective than its counterpart. We also analyze the impact of anatomy ratio on our AWCL framework and find that using more distinct but anatomically similar samples to compose positive pairs results in better quality representations. Extensive experiments on a large-scale fetal ultrasound dataset demonstrate that our approach is effective for learning representations that transfer well to three clinical downstream tasks, and achieves superior performance compared to ImageNet supervised and the current state-of-the-art contrastive learning methods. In particular, AWCL outperforms ImageNet supervised method by 13.8% and state-of-the-art contrastive-based method by 7.1% on a cross-domain segmentation task. The code is available at https://github.com/JianboJiao/AWCL.

Facial Anatomical Landmark Detection Using Regularized Transfer Learning With Application to Fetal Alcohol Syndrome Recognition.

Fetal alcohol syndrome (FAS) caused by prenatal alcohol exposure can result in a series of cranio-facial anomalies, and behavioral and neurocognitive problems. Current diagnosis of FAS is typically done by identifying a set of facial characteristics, which are often obtained by manual examination. Anatomical landmark detection, which provides rich geometric information, is important to detect the presence of FAS associated facial anomalies. This imaging application is characterized by large variations in data appearance and limited availability of labeled data. Current deep learning-based heatmap regression methods designed for facial landmark detection in natural images assume availability of large datasets and are therefore not well-suited for this application. To address this restriction, we develop a new regularized transfer learning approach that exploits the knowledge of a network learned on large facial recognition datasets. In contrast to standard transfer learning which focuses on adjusting the pre-trained weights, the proposed learning approach regularizes the model behavior. It explicitly reuses the rich visual semantics of a domain-similar source model on the target task data as an additional supervisory signal for regularizing landmark detection optimization. Specifically, we develop four regularization constraints for the proposed transfer learning, including constraining the feature outputs from classification and intermediate layers, as well as matching activation attention maps in both spatial and channel levels. Experimental evaluation on a collected clinical imaging dataset demonstrate that the proposed approach can effectively improve model generalizability under limited training samples, and is advantageous to other approaches in the literature.

End-to-end First Trimester Fetal Ultrasound Video Automated CRL and NT Segmentation.

This study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK Fetal Abnormality Screening Programme. A Nested Hourglass (NHG) based network performs semantic pixel-wise segmentation to extract NT and CRL structures. Our results show that the NHG network is faster (19.52% < GFlops than FCN32) and offers high pixel agreement (mean-IoU=80.74) with expert manual annotations.

An overview of polyester/hydroxyapatite composites for bone tissue repairing.

OBJECTIVES: The polyester/hydroxyapatite (polyester/HA) composites play an important role in bone tissue repairing, mostly because they mimic the composition and structure of naturally mineralized bone tissue. This review aimed to discuss commonly used geometries of polyester/HA composites, including microspheres, membranes, scaffolds and bulks, and their applications in bone tissue repairing and to discuss existed restrictions and developing trends of polyester/HA. METHODS: The current review was conducted by searching Web of Science, and Google Scholar for relevant studies published related with polyester/HA composites. Selected studies were analyzed with a focus on the fabrication techniques, properties (mechanical properties, biodegradable properties and biological properties) and applications of polyester/HA composites in bone repairing. RESULTS: A total of 111 articles were introduced to discuss the review. Different geometries of polyester/HA composites were discussed. In addition, properties and applications of polyester/HA composites were evaluated. The addition of HA into polyester can adjust the mechanical and biodegradability of composites. Besides, the addition of HA into polyester can improve its osteogenic abilities. The results showed that polyester/HA composites can ideal candidate for bone tissue repairing. CONCLUSION: Polyester/HA composites have many remarkable properties, such as appropriate mechanical strength, biodegradability, favorable biological properties. Diverse geometries of polyester/HA composites have been used in bone repairing, drug delivery and implant fixation. Further work needs to be done to investigate existed restrictions, including the controlled degradation rate, controlled drug release performance, well-matched mechanical properties, and novel fabrication techniques. THE TRANSLATIONAL POTENTIAL OF THIS ARTICLE: The present review reveals the current state of the polyester/HA composites used in bone tissue repairing, contributing to future trends of polyester/HA composites in the forthcoming future.

Kinsenoside Alleviates Alcoholic Liver Injury by Reducing Oxidative Stress, Inhibiting Endoplasmic Reticulum Stress, and Regulating AMPK-Dependent Autophagy.

Background: Anoectochilus roxburghii (Orchidaceae) is a traditional Chinese medicinal herb with anti-inflammatory, antilipemic, liver protective, immunomodulatory, and other pharmacological activities. Kinsenoside (KD), which shows protective effects against a variety types of liver damage, is an active ingredient extracted from A. roxburghii. However, the liver protective effects and potential mechanisms of KD in alcoholic liver disease (ALD) remain unclear. This study aimed to investigate the liver protective activity and potential mechanisms of KD in ALD. Methods: AML12 normal mouse hepatocyte cells were used to detect the protective effect of KD against ethanol-induced cell damage. An alcoholic liver injury model was induced by feeding male C57BL/6J mice with an ethanol-containing liquid diet, in combination with intraperitoneal administration of 5% carbon tetrachloride (CCl4) in olive oil. Mice were divided into control, model, silymarin (positive control), and two KD groups, treated with different doses. After treatment, hematoxylin-eosin and Masson's trichrome staining of liver tissues was performed, and serum alanine aminotransferase (ALT) and aspartate transaminase (AST) levels were determined to assess the protective effect of KD against alcoholic liver injury. Moreover, proteomics techniques were used to explore the potential mechanism of KD action, and ELISA assay, immunohistochemistry, TUNEL assay, and western blotting were used to verify the mechanism. Results: The results showed that KD concentration-dependently reduced ethanol-induced lipid accumulation in AML12 cells. In ALD mice model, the histological examination of liver tissues, combined with the determination of ALT and AST serum levels, demonstrated a protective effect of KD in the alcoholic liver injury mice. In addition, KD treatment markedly enhanced the antioxidant capacity and reduced the endoplasmic reticulum (ER) stress, inflammation, and apoptosis compared with those in the model group. Furthermore, KD increased the phosphorylation level of AMP-activated protein kinase (AMPK), inhibited the mechanistic target of rapamycin, promoted the phosphorylation of ULK1 (Ser555), increased the level of the autophagy marker LC3A/B, and restored ethanol-suppressed autophagic flux, thus activating AMPK-dependent autophagy. Conclusion: This study indicates that KD alleviates alcoholic liver injury by reducing oxidative stress and ER stress, while activating AMPK-dependent autophagy. All results suggested that KD may be a potential therapeutic agent for ALD.

21-nt phasiRNAs direct target mRNA cleavage in rice male germ cells.

In grasses, phased small interfering RNAs (phasiRNAs), 21- or 24-nucleotide (nt) in length, are predominantly expressed in anthers and play a role in regulating male fertility. However, their targets and mode of action on the targets remain unknown. Here we profile phasiRNA expression in premeiotic and meiotic spikelets as well as in purified male meiocytes at early prophase I, tetrads and microspores in rice. We show that 21-nt phasiRNAs are most abundant in meiocytes at early prophase I while 24-nt phasiRNAs are more abundant in tetrads and microspores. By performing highly sensitive degradome sequencing, we find that 21-nt phasiRNAs direct target mRNA cleavage in male germ cells, especially in meiocytes at early prophase I. These targets include 435 protein-coding genes and 71 transposons that show an enrichment for carbohydrate biosynthetic and metabolic pathways. Our study provides strong evidence that 21-nt phasiRNAs act in a target-cleavage mode and may facilitate the progression of meiosis by fine-tuning carbohydrate biosynthesis and metabolism in male germ cells.

Identification and expression of genes associated with the abscission layer controlling seed shattering in Lolium perenne.

Perennial ryegrass (Lolium perenne) is one of the most important pasture grasses in the world. However, seed production is negatively impacted by the seed shattering (shedding) nature of this species. Recently, genes involved in the seed shattering process have been isolated and functionally characterized in several crop species. The aim of this study was to identify the genes playing critical roles in the seed shattering process in perennial ryegrass. DNA sequences of genes involved in seed shattering in the Poaceae were used to identify and isolate target genes in perennial ryegrass using a comparative genomics strategy. The candidate seed shattering genes were identified using an 'in-house' perennial ryegrass transcriptome database. The relative expression levels of the candidate ryegrass shattering genes were determined using RT-qPCR during different floret and seed developmental stages. Histological analysis of the abscission layer was also conducted. Homologues of seed shattering genes were identified and isolated from perennial ryegrass, and the relative gene expression results suggested that several genes, including LpqSH1 and LpSH1, might have a role in abscission layer formation during seed development. In addition, lignification of the abscission layer may play an important role in the abscission process. A genetic model for seed shattering in perennial ryegrass is suggested and may be useful for directing gene editing towards the production of a reduced-shattering ryegrass.

Multi-Features Fusion for Fault Diagnosis of Pedal Robot Using Time-Speed Signals.

In order to realize automation of the pollutant emission tests of vehicles, a pedal robot is designed instead of a human-driven vehicle. Sometimes, the actual time-speed curve of the vehicle will deviate from the upper or lower limit of the worldwide light-duty test cycle (WLTC) target curve, which will cause a fault. In this paper, a new fault diagnosis method is proposed and applied to the pedal robot. Since principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and Autoencoder cannot extract feature information adequately when they are used alone, three types of feature components extracted by PCA, t-SNE, and Autoencoder are fused to form a nine-dimensional feature set. Then, the feature set is reduced into three-dimensional space via Treelet Transform. Finally, the fault samples are classified by Gaussian process classifier. Compared with the methods using only one algorithm to extract features, the proposed method has the minimum standard deviation, 0.0078, and almost the maximum accuracy, 98.17%. The accuracy of the proposed method is only 0.24% lower than that without Treelet Transform, but the processing time is 6.73% less than that without Treelet Transform. These indicate that the multi-features fusion model and Treelet Transform method is quite effective. Therefore, the proposed method is quite helpful for fault diagnosis of the pedal robot.