Unsupervised outlier detection is a vital task and has high impact on a wide variety of applications domains, such as image analysis and video surveillance. It also gains long-standing attentions and ...has been extensively studied in multiple research areas. Detecting and taking action on outliers as quickly as possible are imperative in order to protect network and related stakeholders or to maintain the reliability of critical systems. However, outlier detection is difficult due to the one class nature and challenges in feature construction. Sequential anomaly detection is even harder with more challenges from temporal correlation in data, as well as the presence of noise and high dimensionality. In this paper, we introduce a novel deep structured framework to solve the challenging sequential outlier detection problem. We use autoencoder models to capture the intrinsic difference between outliers and normal instances and integrate the models to recurrent neural networks that allow the learning to make use of previous context as well as make the learners more robust to warp along the time axis. Furthermore, we propose to use a layerwise training procedure, which significantly simplifies the training procedure and hence helps achieve efficient and scalable training. In addition, we investigate a fine-tuning step to update all parameters set by incorporating the temporal correlation in the sequence. We further apply our proposed models to conduct systematic experiments on five real-world benchmark data sets. Experimental results demonstrate the effectiveness of our model, compared with other state-of-the-art approaches.
In recent years, intelligent fault diagnosis technology with the deep learning algorithm has been widely used in the manufacturing industry for substituting time-consuming human analysis method to ...enhance the efficiency of fault diagnosis. The rolling bearing as the connection between the rotor and support is the crucial component in rotating equipment. However, the working condition of the rolling bearing is under changing with complex operation demand, which will significantly degrade the performance of the intelligent fault diagnosis method. In this paper, a new deep transfer model based on Wasserstein distance guided multi-adversarial networks (WDMAN) is proposed to address this problem. The WDMAN model exploits complex feature space structures to enable the transfer of different data distributions based on multiple domain critic networks. The essence of our method is learning the shared feature representation by minimizing the Wasserstein distance between the source domain and target domain distribution in an adversarial training way. The experiment results demonstrate that our model outperforms the state-of-the-art methods on rolling bearing fault diagnosis under different working conditions. The t-distributed stochastic neighbor embedding (t-SNE) technology is used to visualize the learned domain invariant feature and investigate the transferability behind the great performance of our proposed model.
Lower urinary tract development and disease Rasouly, Hila Milo; Lu, Weining
Wiley interdisciplinary reviews. Systems biology and medicine,
May/June 2013, Letnik:
5, Številka:
3
Journal Article
Recenzirano
Odprti dostop
Congenital anomalies of the lower urinary tract (CALUT) are a family of birth defects of the ureter, the bladder, and the urethra. CALUT includes ureteral anomaliesc such as congenital abnormalities ...of the ureteropelvic junction (UPJ) and ureterovesical junction (UVJ), and birth defects of the bladder and the urethra such as bladder‐exstrophy‐epispadias complex (BEEC), prune belly syndrome (PBS), and posterior urethral valves (PUVs). CALUT is one of the most common birth defects and is often associated with antenatal hydronephrosis, vesicoureteral reflux (VUR), urinary tract obstruction, urinary tract infections (UTI), chronic kidney disease, and renal failure in children. Here, we discuss the current genetic and molecular knowledge about lower urinary tract development and genetic basis of CALUT in both human and mouse models. We provide an overview of the developmental processes leading to the formation of the ureter, the bladder, and the urethra, and different genes and signaling pathways controlling these developmental processes. Human genetic disorders that affect the ureter, the bladder and the urethra and associated gene mutations are also presented. As we are entering the postgenomic era of personalized medicine, information in this article may provide useful interpretation for the genetic and genomic test results collected from patients with lower urinary tract birth defects. With evidence‐based interpretations, clinicians may provide more effective personalized therapies to patients and genetic counseling for their families. WIREs Syst Biol Med 2013, 5:307–342. doi: 10.1002/wsbm.1212
This article is categorized under:
Developmental Biology > Developmental Processes in Health and Disease
Translational, Genomic, and Systems Medicine > Translational Medicine
Pose estimation from points with unknown correspondences currently is still a difficult problem in the field of computer vision. To solve this problem, the SoftSI algorithm is proposed, which can ...simultaneously obtain pose and correspondences. The SoftSI algorithm is based on the combination of the proposed PnP algorithm (the SI algorithm) and two singular value decomposition (SVD)-based shape description theorems. Other main contributions of this paper are: 1) two SVD-based shape description theorems are proposed; 2) by analyzing the calculation process of the SI algorithm, the method to avoid pose ambiguity is proposed; and 3) an acceleration method to quickly eliminate bad initial values for the SoftSI algorithm is proposed. The simulation results show that the SI algorithm is accurate while the SoftSI algorithm is fast, robust to noise, and has large convergence radius.
Wireless capsule endoscopy (WCE) has become an irreplaceable tool for diagnosing small intestinal diseases, and detecting the outliers in WCE images automatically remains as a hot research topic. ...Considering the difficulties in obtaining sufficient labeled WCE data, it is necessary to develop the diagnosis model which works well with only little labeled or even unlabeled training samples. In this paper, a novel semi-supervised deep-structured framework is introduced to solve the problem of outlier detection in WCE images. The key idea of our model is to mine the anomalous graphical patterns existed in the image by analyzing the spatial-scale trends of sequential image regions. Three main contributions are concluded: 1) we integrate a convolutional neural network into long short term memory network, so that the intrinsic differences between outliers and normal instances could be captured. Besides, 2) a assessment model is built by using various signs of anomaly occurrence and fake outliers knowledge learned during the training stage, which enhances the outlier alarm accuracy significantly. Furthermore, 3) a nest-structured training method is proposed, which helps our model achieving efficient training process. Experimental results on the real WCE images demonstrate the effectiveness of our model.
Slit guidance ligand 2 (SLIT2) is a large, secreted protein that binds roundabout (ROBO) receptors on multiple cell types, including neurons and kidney podocytes. SLIT2-ROBO–mediated signaling ...regulates neuronal migration and ureteric bud (UB) outgrowth during kidney development as well as glomerular filtration in adult kidneys. Additionally, SLIT2 binds Gremlin, an antagonist of bone morphogenetic proteins (BMPs), and BMP–Gremlin signaling also regulates UB formation. However, direct cross-talk between the ROBO2–SLIT2 and BMP–Gremlin signaling pathways has not been established. Here, we report the discovery of negative feedback between the SLIT2 and BMP–Gremlin signaling pathways. We found that the SLIT2–Gremlin interaction inhibited both SLIT2–ROBO2 signaling in neurons and Gremlin antagonism of BMP activity in myoblasts and fibroblasts. Furthermore, BMP2 down-regulated SLIT2 expression and promoter activity through canonical BMP signaling. Gremlin treatment, BMP receptor inhibition, and SMAD family member 4 (SMAD4) knockdown rescued BMP-mediated repression of SLIT2. BMP2 treatment of nephron progenitor cells derived from human embryonic stem cells decreased SLIT2 expression, further suggesting an interaction between the BMP2–Gremlin and SLIT2 pathways in human kidney cells. In conclusion, our study has revealed direct negative cross-talk between two pathways, previously thought to be unassociated, that may regulate both kidney development and adult tissue maintenance.
Several proteins implicated in the pathogenesis of polycystic kidney disease (PKD) localize to cilia. Furthermore, cilia are malformed in mice with PKD with mutations in TgN737Rpw (encoding polaris). ...It is not known, however, whether ciliary dysfunction occurs or is relevant to cyst formation in PKD. Here, we show that polycystin-1 (PC1) and polycystin-2 (PC2), proteins respectively encoded by Pkd1 and Pkd2, mouse orthologs of genes mutated in human autosomal dominant PKD, co-distribute in the primary cilia of kidney epithelium. Cells isolated from transgenic mice that lack functional PC1 formed cilia but did not increase Ca(2+) influx in response to physiological fluid flow. Blocking antibodies directed against PC2 similarly abolished the flow response in wild-type cells as did inhibitors of the ryanodine receptor, whereas inhibitors of G-proteins, phospholipase C and InsP(3) receptors had no effect. These data suggest that PC1 and PC2 contribute to fluid-flow sensation by the primary cilium in renal epithelium and that they both function in the same mechanotransduction pathway. Loss or dysfunction of PC1 or PC2 may therefore lead to PKD owing to the inability of cells to sense mechanical cues that normally regulate tissue morphogenesis.
Roundabout guidance receptor 2 (ROBO2) plays an important role during early kidney development. ROBO2 is expressed in podocytes, inhibits nephrin-induced actin polymerization, down-regulates ...nonmuscle myosin IIA activity, and destabilizes kidney podocyte adhesion. However, the role of ROBO2 during kidney injury, particularly in mature podocytes, is not known. Herein, we report that loss of ROBO2 in podocytes Robo2 conditional knockout (cKO) mouse is protective from glomerular injuries. Ultrastructural analysis reveals that Robo2 cKO mice display less foot process effacement and better-preserved slit-diaphragm density compared with wild-type littermates injured by either protamine sulfate or nephrotoxic serum (NTS). The Robo2 cKO mice also develop less proteinuria after NTS injury. Further studies reveal that ROBO2 expression in podocytes is up-regulated after glomerular injury because its expression levels are higher in the glomeruli of NTS injured mice and passive Heymann membranous nephropathy rats. Moreover, the amount of ROBO2 in the glomeruli is also elevated in patients with membranous nephropathy. Finally, overexpression of ROBO2 in cultured mouse podocytes compromises cell adhesion. Taken together, these findings suggest that kidney injury increases glomerular ROBO2 expression that might compromise podocyte adhesion and, thus, loss of Robo2 in podocytes could protect from glomerular injury by enhancing podocyte adhesion that helps maintain foot process structure. Our findings also suggest that ROBO2 is a therapeutic target for podocyte injury and podocytopathy.
Cooperative planning is one of the critical problems in the field of multi-agent system gaming. This work focuses on cooperative planning when each agent has only a local observation range and local ...communication. We propose a novel cooperative planning architecture that combines a graph neural network with a task-oriented knowledge fusion sampling method. Two main contributions of this paper are based on the comparisons with previous work: (1) we realize feasible and dynamic adjacent information fusion using GraphSAGE (i.e., Graph SAmple and aggreGatE), which is the first time this method has been used to deal with the cooperative planning problem, and (2) a task-oriented sampling method is proposed to aggregate the available knowledge from a particular orientation, to obtain an effective and stable training process in our model. Experimental results demonstrate the good performance of our proposed method.
Congenital anomalies of the kidneys and urinary tract (CAKUT) are the most common cause of chronic kidney disease in the first three decades of life. Identification of single-gene mutations that ...cause CAKUT permits the first insights into related disease mechanisms. However, for most cases the underlying defect remains elusive. We identified a kindred with an autosomal-dominant form of CAKUT with predominant ureteropelvic junction obstruction. By whole exome sequencing, we identified a heterozygous truncating mutation (c.1010delG) of T-Box transcription factor 18 (TBX18) in seven affected members of the large kindred. A screen of additional families with CAKUT identified three families harboring two heterozygous TBX18 mutations (c.1570C>T and c.487A>G). TBX18 is essential for developmental specification of the ureteric mesenchyme and ureteric smooth muscle cells. We found that all three TBX18 altered proteins still dimerized with the wild-type protein but had prolonged protein half life and exhibited reduced transcriptional repression activity compared to wild-type TBX18. The p.Lys163Glu substitution altered an amino acid residue critical for TBX18-DNA interaction, resulting in impaired TBX18-DNA binding. These data indicate that dominant-negative TBX18 mutations cause human CAKUT by interference with TBX18 transcriptional repression, thus implicating ureter smooth muscle cell development in the pathogenesis of human CAKUT.