With the popular use of high-resolution satellite images, more and more research efforts have been placed on remote sensing scene classification/recognition. In scene classification, effective ...feature selection can significantly boost the final performance. In this letter, a novel deep-learning-based feature-selection method is proposed, which formulates the feature-selection problem as a feature reconstruction problem. Note that the popular deep-learning technique, i.e., the deep belief network (DBN), achieves feature abstraction by minimizing the reconstruction error over the whole feature set, and features with smaller reconstruction errors would hold more feature intrinsics for image representation. Therefore, the proposed method selects features that are more reconstructible as the discriminative features. Specifically, an iterative algorithm is developed to adapt the DBN to produce the inquired reconstruction weights. In the experiments, 2800 remote sensing scene images of seven categories are collected for performance evaluation. Experimental results demonstrate the effectiveness of the proposed method.
Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which bring great ...challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack-an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack representation. In this method, multi-scale deep convolutional features learned at hierarchical convolutional stages are fused together to capture the line structures. More detailed representations are made in larger scale feature maps and more holistic representations are made in smaller scale feature maps. We build DeepCrack net on the encoder-decoder architecture of SegNet and pairwisely fuse the convolutional features generated in the encoder network and in the decoder network at the same scale. We train DeepCrack net on one crack dataset and evaluate it on three others. The experimental results demonstrate that DeepCrack achieves F -measure over 0.87 on the three challenging datasets in average and outperforms the current state-of-the-art methods.
Lane detection in driving scenes is an important module for autonomous vehicles and advanced driver assistance systems. In recent years, many sophisticated lane detection methods have been proposed. ...However, most methods focus on detecting the lane from one single image, and often lead to unsatisfactory performance in handling some extremely-bad situations such as heavy shadow, severe mark degradation, serious vehicle occlusion, and so on. In fact, lanes are continuous line structures on the road. Consequently, the lane that cannot be accurately detected in one current frame may potentially be inferred out by incorporating information of previous frames. To this end, we investigate lane detection by using multiple frames of a continuous driving scene, and propose a hybrid deep architecture by combining the convolutional neural network (CNN) and the recurrent neural network (RNN). Specifically, information of each frame is abstracted by a CNN block, and the CNN features of multiple continuous frames, holding the property of time-series, are then fed into the RNN block for feature learning and lane prediction. Extensive experiments on two large-scale datasets demonstrate that, the proposed method outperforms the competing methods in lane detection, especially in handling difficult situations.
The closely regulated process of mRNA translation is crucial for precise control of protein abundance and quality. Ribosome profiling, a combination of ribosome foot-printing and RNA deep sequencing, ...has been used in a large variety of studies to quantify genome-wide mRNA translation. Here, we developed Xtail, an analysis pipeline tailored for ribosome profiling data that comprehensively and accurately identifies differentially translated genes in pairwise comparisons. Applied on simulated and real datasets, Xtail exhibits high sensitivity with minimal false-positive rates, outperforming existing methods in the accuracy of quantifying differential translations. With published ribosome profiling datasets, Xtail does not only reveal differentially translated genes that make biological sense, but also uncovers new events of differential translation in human cancer cells on mTOR signalling perturbation and in human primary macrophages on interferon gamma (IFN-γ) treatment. This demonstrates the value of Xtail in providing novel insights into the molecular mechanisms that involve translational dysregulations.
Developing highly efficient and low‐cost photocatalysts for overall water splitting has long been a pursuit for converting solar power into clean hydrogen energy. Herein, we demonstrate that a ...nonstoichiometric nickel–cobalt double hydroxide can achieve overall water splitting by itself upon solar light irradiation, avoiding the consumption of noble‐metal co‐catalysts. We employed an intensive laser to ablate a NiCo alloy target immersed in alkaline solution, and produced so‐called L‐NiCo nanosheets with a nonstoichiometric composition and O2−/Co3+ ions exposed on the surface. The nonstoichiometric composition broadens the band gap, while O2− and Co3+ ions boost hydrogen and oxygen evolution, respectively. As such, the photocatalyst achieves a H2 evolution rate of 1.7 μmol h−1 under AM 1.5G sunlight irradiation and an apparent quantum yield (AQE) of 1.38 % at 380 nm.
A single‐phase photocatalyst, a hydrogen‐deficient nickel–cobalt double hydroxide, was generated by laser ablation. This photocatalyst can drive overall water splitting under solar light irradiation in the absence of sacrificial agents and noble metal co‐catalysts because of its unique composition and structure, with partially removed hydrogen atoms as well as O2− and Co3+ ions exposed on the surface.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
► A method for fully-automatic crack detection from pavement images. ► A geodesic shadow-removal algorithm that can remove the pavement shadows while preserve the cracks. ► A sequential ...implementation of ball voting and stick voting that enhances the crack curves. ► An MST construction and edge pruning for reducing false positives. ► A collection of 206 pavement images for performance evaluation.
Pavement cracks are important information for evaluating the road condition and conducting the necessary road maintenance. In this paper, we develop
CrackTree, a fully-automatic method to detect cracks from pavement images. In practice, crack detection is a very challenging problem because of (1) low contrast between cracks and the surrounding pavement, (2) intensity inhomogeneity along the cracks, and (3) possible shadows with similar intensity to the cracks. To address these problems, the proposed method consists of three steps. First, we develop a geodesic shadow-removal algorithm to remove the pavement shadows while preserving the cracks. Second, we build a crack probability map using tensor voting, which enhances the connection of the crack fragments with good proximity and curve continuity. Finally, we sample a set of crack seeds from the crack probability map, represent these seeds by a graph model, derive minimum spanning trees from this graph, and conduct recursive tree-edge pruning to identify desirable cracks. We evaluate the proposed method on a collection of 206 real pavement images and the experimental results show that the proposed method achieves a better performance than several existing methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Rail surface defects such as the abrasion, scratch and peeling often cause damages to the train wheels and rail bearings. An efficient and accurate detection of rail defects is of vital importance ...for the safety of railway transportation. In the past few decades, automatic rail defect detection has been studied; however, most developed methods use optic-imaging techniques to collect the rail surface data and are still suffering from a high false recognition rate. In this paper, a novel 3D laser profiling system (3D-LPS) is proposed, which integrates a laser scanner, odometer, inertial measurement unit (IMU) and global position system (GPS) to capture the rail surface profile data. For automatic defect detection, first, the deviation between the measured profile and a standard rail model profile is computed for each laser-imaging profile, and the points with large deviations are marked as candidate defect points. Specifically, an adaptive iterative closest point (AICP) algorithm is proposed to register the point sets of the measured profile with the standard rail model profile, and the registration precision is improved to the sub-millimeter level. Second, all of the measured profiles are combined together to form the rail surface through a high-precision positioning process with the IMU, odometer and GPS data. Third, the candidate defect points are merged into candidate defect regions using the K-means clustering. At last, the candidate defect regions are classified by a decision tree classifier. Experimental results demonstrate the effectiveness of the proposed laser-profiling system in rail surface defect detection and classification.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Elevated expression of RNA binding protein HNRNPC has been reported in cancer cells, while the essentialness and functions of HNRNPC in tumors were not clear. We showed that repression of HNRNPC in ...the breast cancer cells MCF7 and T47D inhibited cell proliferation and tumor growth. Our computational inference of the key pathways and extensive experimental investigations revealed that the cascade of interferon responses mediated by RIG‐I was responsible for such tumor‐inhibitory effect. Interestingly, repression of HNRNPC resulted in accumulation of endogenous double‐stranded RNA (dsRNA), the binding ligand of RIG‐I. These up‐regulated dsRNA species were highly enriched by Alu sequences and mostly originated from pre‐mRNA introns that harbor the known HNRNPC binding sites. Such source of dsRNA is different than the recently well‐characterized endogenous retroviruses that encode dsRNA. In summary, essentialness of HNRNPC in the breast cancer cells was attributed to its function in controlling the endogenous dsRNA and the down‐stream interferon response. This is a novel extension from the previous understandings about HNRNPC in binding with introns and regulating RNA splicing.
Synopsis
Repression of RNA binding protein HNRNPC in breast cancer cells MCF7 and T47D resulted in accumulation of endogenous dsRNA species mostly from Alu introns, which triggered interferon response and tumor growth arrest.
HNRNPC is highly expressed in breast cancer tumors and repression of HNRNPC arrests proliferation of MCF7 and T47D cells.
Interferon response mediated by RNA sensor RIG‐I is responsible for anti‐proliferation effect of HNRNPC repression.
Repression of HNRNPC induces immunostimulatory endogenous dsRNA mostly from introns with Alu.
Production of Alu dsRNA can be traced back to RNA quality control machinery such as nonsense‐mediated decay.
Repression of the RNA binding protein HNRNPC in breast cancer cells causes accumulation of endogenous dsRNA species leading to interferon response and tumor growth arrest.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Metallic catalysts with nanopores are advantageous on improving both activity and selectivity, while the reason behind that remains unclear all along. In this work, porous Zn nanoparticles (P‐Zn) ...were adopted as a model catalyst to investigate the catalytic behavior of metallic nanopores. In situ X‐ray absorption spectroscopy, in situ Fourier transform infrared spectroscopy, and density functional theory (DFT) analyses reveal that the concave surface of nanopores works like a pincer to capture and clamp CO2 and H2O precursors simultaneously, thus lowering the energy barriers of CO2 electroreduction. Resultantly, the pincer mechanism endows P‐Zn with a high Faradic efficiency (98.1 %) towards CO production at the potential of −0.95 V vs. RHE. Moreover, DFT calculation demonstrates that Co and Cu nanopores exhibit the pincer behavior as well, suggesting that this mechanism is universal for metallic nanopores.
In situ analytic techniques and theoretical calculations were employed to investigate the electroreduction of CO2 in metallic nanopores. It was found that the concave surface of metallic nanopores works like a pincer to capture and clamp CO2 and H2O precursors simultaneously, thus lowering the energy barriers of CO2 electroreduction.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Abstract
A major part of the transcriptome complexity is attributed to multiple types of DNA or RNA fusion events, which take place within a gene such as alternative splicing or between different ...genes such as DNA rearrangement and trans-splicing. In the present study, using the RNA deep sequencing data, we systematically survey a type of non-canonical fusions between the RNA transcripts from the two opposite DNA strands. We name the products of such fusion events cross-strand chimeric RNA (cscRNA). Hundreds to thousands of cscRNAs can be found in human normal tissues, primary cells, and cancerous cells, and in other species as well. Although cscRNAs exhibit strong tissue-specificity, our analysis identifies thousands of recurrent cscRNAs found in multiple different samples. cscRNAs are mostly originated from convergent transcriptions of the annotated genes and their anti-sense DNA. The machinery of cscRNA biogenesis is unclear, but the cross-strand junction events show some features related to RNA splicing. The present study is a comprehensive survey of the non-canonical cross-strand RNA junction events, a resource for further characterization of the originations and functions of the cscRNAs.