A central theme in learning from image data is to develop appropriate representations for the specific task at hand. Thus, a practical challenge determine what features are tasks. For example, study of gene expression patterns <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Drosophila</i> , texture were particularly effective determining developmental stages situ hybridization images. Such representation however not suitable controlled...

Digital reconstruction, or tracing, of 3-D neuron structure from microscopy images is a critical step toward reversing engineering the wiring and anatomy brain. Despite number prior attempts, this task remains very challenging, especially when are contaminated by noises have discontinued segments neurite patterns. An approach for addressing such problems to identify locations neuronal voxels using image segmentation methods, applying tracing reconstruction techniques. This preprocessing...

A central theme in learning from image data is to develop appropriate representations for the specific task at hand. Traditional methods used handcrafted local features combined with high-level generate image-level representations. Thus, a practical challenge determine what are tasks. For example, study of gene expression patterns Drosophila melanogaster, texture based on wavelets were particularly effective determining developmental stages situ hybridization (ISH) images. Such...

The detection of secondary structure proteins using three dimensional (3D) cryo-electron microscopy (cryo-EM) images is still a challenging task when the spatial resolution cryo-EM at medium level (5-10Å). Prior researches focused on usage local features that may not capture global information image objects. In this study, we propose to use deep learning methods extract high representative and then automatically detect structures proteins. particular, build convolutional neural network (CNN)...

Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D situ hybridization (ISH) patterns multiple developing stages mouse brain. Currently, ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach annotate pattern structural levels over course development. We applied...

In the deep geological repository of nuclear waste, corrosion waste generates gas, which increases storage pressure, changes properties rock strata, and affects stability repository. Therefore, it is great importance to understand gas migration in engineering barrier potential impact on its integrity for safety assessment A hydro-mechanical-damage model analyzing sedimentary rocks established this paper. On basis which, a set coupled formulas coupling mass established. The considers...

Loss of matric suction during rain has an important effect on the instability expansive soil slope. A new device was designed for testing force in order to propose and determine equivalent corresponding suction. First, internal relation between unsaturated analyzed. Then, numerical algorithm implementation discussed, introduced into strength reduction finite element method (FEM). Finally, effects were compared analyzed by evaluating stability The results show that significantly improves...

Traditional clustering and feature selection methods consider the data matrix as static. However, matrices evolve smoothly over time in many applications. A simple approach to learn from these time-evolving is analyze them separately. Such strategy ignores time-dependent nature of underlying data. In this paper, we propose two formulations for evolutionary co-clustering based on fused Lasso regularization. The formulation able identify varying hidden block structures embedded into along...

Existing model tests for reinforcing loess slopes with stabilizing piles are often challenged by simulation inaccuracies in lateral loading modes and scaling. Addressing these concerns, this study conducts numerical simulations to scrutinize the damage characteristics of concrete two varying slope conditions under non-uniform loading. The were designed strictly maintain similarity ratio piles. results reveal a no table 20% reduction bearing capacity due penetration potential sliding surface,...

Differential gene expression patterns in cells of the mammalian brain result morphological, connectional, and functional diversity cells. A wide variety studies have shown that certain genes are expressed only specific cell-types. Analysis cell-type-specific can provide insights into relationship between genes, connectivity, regions, However, automated methods for identifying lacking to date. Here, we describe a set computational mouse by image computing situ hybridization (ISH) patterns. We...

When tests are conducted on the field slope under artificial rainfall, because rainfall is often limited to implementation in mode of local there a boundary constraint effect between area and non-rainfall area, which manifested lateral infiltration rainwater deformation retardation area. Firstly, deep-buried isolated trench was proposed solve these constraints. Then, cracking corresponding numerical simulation were rainfall. In end, response water content failure characteristics analyzed...

The contribution of matric suction to the stability an unsaturated soil slope must be properly accounted for in order evaluate with reasonable accuracy. It is also essential develop a better method analyze instead conventional slice commonly used practice so far. In this paper, previous research work on strength reviewed and formulation proposed three-dimensional effective stress space. implementation reduction analysis using Finite Element Method (FEM) described paper. A case history...

It is of great theoretical and engineering significance to carry out field rainfall tests research on double-layer soil slopes in loess areas. Based the developed simulation system with slow-moving injection, were carried a natural slope. The characteristics volumetric water content monitored, infiltration effect at interface layer analyzed by numerical simulation. results showed fastest top platform slope, followed that upper surface slowest lower slope during rainfall. Under various...

Abstract Background Multicellular organisms consist of cells many different types that are established during development. Each type cell is characterized by the unique combination expressed gene products as a result spatiotemporal regulation. Currently, fundamental challenge in regulatory biology to elucidate expression controls generate complex body plans Recent advances high-throughput biotechnologies have generated patterns for thousands genes model organism fruit fly Drosophila...

Cryo-electron microscopy (cryo-EM) is an emerging biophysical technique for structural determination of protein complexes. However, accurate detection secondary structures still challenging when cryo-EM density maps are at medium resolutions (5-10 Å). Most existing methods image processing that do not fully utilize available images in the database. In this paper, we present a deep learning approach to segment structure elements as helices and β-sheets from medium-resolution maps. The...