Randomness Evaluation for Scrambled Image Using Intersecting Cortical Model Neural Network

2014 ◽  
Vol 530-531 ◽  
pp. 434-442
Author(s):  
Jing Jing Zhao ◽  
Guang Zhu Xu ◽  
Bang Jun Lei ◽  
Chun Lin Li
Keyword(s):  
Neural Network ◽  
Structural Information ◽  
Cortical Model ◽  
Image Scrambling ◽  
Human Visual Perception ◽  
L1 Norm ◽  
Structure Information ◽  
Binary Images ◽  
Input Field ◽  
Evaluation Algorithm

A bio-inspired visual neural network named ICMNN was adopted to extract image structural information for image scrambling evaluation. In order to describe image structure more effectively with ICMNN, image bitmap was introduced into ICMNN input field. First, the original image was decomposed into eight binary images and each was scrambled with Arnold transformation without loss of generality. Then, ICMNN was adopted to extract the structural feature sequence of bitmap images and their corresponding scrambled ones. Last, L1 norm of the structure change sequence between them was calculated to evaluate the scrambling degree of the scrambling images. Results show that combining image bitmap decomposition with ICMNN can effectively evaluate image scrambling degree and describe the change of the structure information, which agrees with human visual perception. This evaluation algorithm is also independent of the scrambling algorithm and has a good versatility.

scholarly journals Bert-Enhanced Text Graph Neural Network for Classification

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1536
Author(s):  
Yiping Yang ◽  
Xiaohui Cui
Keyword(s):  
Neural Network ◽  
Semantic Information ◽  
Structural Information ◽  
Text Processing ◽  
Language Model ◽  
Research Direction ◽  
Semantic Features ◽  
Structure Information ◽  
Single Text ◽  
Graph Neural Networks

Text classification is a fundamental research direction, aims to assign tags to text units. Recently, graph neural networks (GNN) have exhibited some excellent properties in textual information processing. Furthermore, the pre-trained language model also realized promising effects in many tasks. However, many text processing methods cannot model a single text unit’s structure or ignore the semantic features. To solve these problems and comprehensively utilize the text’s structure information and semantic information, we propose a Bert-Enhanced text Graph Neural Network model (BEGNN). For each text, we construct a text graph separately according to the co-occurrence relationship of words and use GNN to extract text features. Moreover, we employ Bert to extract semantic features. The former part can take into account the structural information, and the latter can focus on modeling the semantic information. Finally, we interact and aggregate these two features of different granularity to get a more effective representation. Experiments on standard datasets demonstrate the effectiveness of BEGNN.

Rapid determination of fractal structure of bacterial assemblages in wastewater treatment: implications to process optimisation

1998 ◽  
Vol 38 (2) ◽  
pp. 9-15 ◽  
Author(s):  
J. Guan ◽  
T. D. Waite ◽  
R. Amal ◽  
H. Bustamante ◽  
R. Wukasch
Keyword(s):  
Wastewater Treatment ◽  
Fractal Structure ◽  
Structural Information ◽  
Rapid Determination ◽  
Fractal Dimensions ◽  
Structure Information ◽  
Treatment Processes ◽  
On Line ◽  
Bacterial Aggregates

A rapid method of determining the structure of aggregated particles using small angle laser light scattering is applied here to assemblages of bacteria from wastewater treatment systems. The structure information so obtained is suggestive of fractal behaviour as found by other methods. Strong dependencies are shown to exist between the fractal structure of the bacterial aggregates and the behaviour of the biosolids in zone settling and dewatering by both pressure filtration and centrifugation methods. More rapid settling and significantly higher solids contents are achievable for “looser” flocs characterised by lower fractal dimensions. The rapidity of determination of structural information and the strong dependencies of the effectiveness of a number of wastewater treatment processes on aggregate structure suggests that this method may be particularly useful as an on-line control tool.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Fused Image Quality Measure Based on Structural Similarity

2011 ◽  
Vol 255-260 ◽  
pp. 2072-2076
Author(s):  
Yi Yong Han ◽  
Jun Ju Zhang ◽  
Ben Kang Chang ◽  
Yi Hui Yuan ◽  
Hui Xu
Keyword(s):  
Image Fusion ◽  
Structural Information ◽  
Similarity Index ◽  
Structural Similarity ◽  
Reference Image ◽  
Human Visual Perception ◽  
Subjective Evaluations ◽  
Fused Image ◽  
Fusion Methods ◽  
Image Quality Measure

Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we present a new approach using structural similarity index for assessing quality in image fusion. The advantages of our measures are that they do not require a reference image and can be easily computed. Numerous simulations demonstrate that our measures are conform to subjective evaluations and can be able to assess different image fusion methods.

scholarly journals TomoSAR Mapping of 3D Forest Structure: Contributions of L-Band Configurations

2021 ◽  
Vol 13 (12) ◽  
pp. 2255
Author(s):  
Matteo Pardini ◽  
Victor Cazcarra-Bes ◽  
Konstantinos Papathanassiou
Keyword(s):  
Information Content ◽  
Forest Structure ◽  
Structural Information ◽  
3D Structure ◽  
Physical Structure ◽  
Structure Mapping ◽  
Structure Information ◽  
Forest Sites ◽  
L Band ◽  
Structure Indices

Synthetic Aperture Radar (SAR) measurements are unique for mapping forest 3D structure and its changes in time. Tomographic SAR (TomoSAR) configurations exploit this potential by reconstructing the 3D radar reflectivity. The frequency of the SAR measurements is one of the main parameters determining the information content of the reconstructed reflectivity in terms of penetration and sensitivity to the individual vegetation elements. This paper attempts to review and characterize the structural information content of L-band TomoSAR reflectivity reconstructions, and their potential to forest structure mapping. First, the challenges in the accurate TomoSAR reflectivity reconstruction of volume scatterers (which are expected to dominate at L-band) and to extract physical structure information from the reconstructed reflectivity is addressed. Then, the L-band penetration capability is directly evaluated by means of the estimation performance of the sub-canopy ground topography. The information content of the reconstructed reflectivity is then evaluated in terms of complementary structure indices. Finally, the dependency of the TomoSAR reconstruction and of its structural information to both the TomoSAR acquisition geometry and the temporal change of the reflectivity that may occur in the time between the TomoSAR measurements in repeat-pass or bistatic configurations is evaluated. The analysis is supported by experimental results obtained by processing airborne acquisitions performed over temperate forest sites close to the city of Traunstein in the south of Germany.

scholarly journals NMR-Based Structural Characterization of a Two-Disulfide-Bonded Analogue of the FXIIIa Inhibitor Tridegin: New Insights into Structure–Activity Relationships

2021 ◽  
Vol 22 (2) ◽  
pp. 880
Author(s):  
Thomas Schmitz ◽  
Ajay Abisheck Paul George ◽  
Britta Nubbemeyer ◽  
Charlotte A. Bäuml ◽  
Torsten Steinmetzer ◽  
...  
Keyword(s):  
Structural Information ◽  
Coagulation Factor ◽  
Md Simulations ◽  
2D Nmr ◽  
Label Free ◽  
2D Nmr Spectroscopy ◽  
Structure Information ◽  
Structure Activity Relationships ◽  
Structure Activity ◽  
Blood Sucking

The saliva of blood-sucking leeches contains a plethora of anticoagulant substances. One of these compounds derived from Haementeria ghilianii, the 66mer three-disulfide-bonded peptide tridegin, specifically inhibits the blood coagulation factor FXIIIa. Tridegin represents a potential tool for antithrombotic and thrombolytic therapy. We recently synthesized two-disulfide-bonded tridegin variants, which retained their inhibitory potential. For further lead optimization, however, structure information is required. We thus analyzed the structure of a two-disulfide-bonded tridegin isomer by solution 2D NMR spectroscopy in a combinatory approach with subsequent MD simulations. The isomer was studied using two fragments, i.e., the disulfide-bonded N-terminal (Lys1–Cys37) and the flexible C-terminal part (Arg38–Glu66), which allowed for a simplified, label-free NMR-structure elucidation of the 66mer peptide. The structural information was subsequently used in molecular modeling and docking studies to provide insights into the structure–activity relationships. The present study will prospectively support the development of anticoagulant-therapy-relevant compounds targeting FXIIIa.

Characterization of Tilt Boundaries by Ultra High Resolution Electron Microscopy

1984 ◽  
Vol 41 ◽  
Author(s):  
W. Krakow ◽  
J. T. Wetzel ◽  
D. A. Smith ◽  
G. Trafas
Keyword(s):  
High Resolution ◽  
Grain Boundary ◽  
Structural Information ◽  
Theoretical Work ◽  
High Resolution Electron Microscopy ◽  
Point Of View ◽  
Experimental Point ◽  
Structure Information ◽  
Resolution Electron ◽  
Tilt Boundaries

AbstractA high resolution electron microscope study of grain boundary structures in Au thin films has been undertaken from both a theoretical and experimental point of view. The criteria necessary to interpret images of tilt boundaries at the atomic level, which include electron optical and specimen effects, have been considered for both 200kV and the newer 400kV medium voltage microscopes. So far, the theoretical work has concentrated on two different [001] tilt bounda-ries where a resolution of 2.03Å is required to visualize bulk lattice structures on either side of the interface. Both a high angle boundary, (210) σ=5, and a low angle boundary, (910) σ=41, have been considered. Computational results using multislice dynamical diffraction and image simulations of relaxed bounda-ries viewed edge-on and with small amounts of beam and/or specimen inclina-tion have been obtained. It will be shown that some structural information concerning grain boundary dislocations can be observed at 200kV. However, many difficulties occur in the exact identification of the interface structure viewed experimentally for both [001] and [011] boundaries since the resolution required is near the performance limit of a 200kV microscope. The simulated results at 400kV indicate a considerable improvement will be realized in obtain-ing atomic structure information at the interface.

scholarly journals Aspect-level sentiment analysis merged with knowledge graph and graph convolutional neural network

2021 ◽  
Vol 2083 (4) ◽  
pp. 042044
Author(s):  
Zuhua Dai ◽  
Yuanyuan Liu ◽  
Shilong Di ◽  
Qi Fan
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Structural Information ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Text Data ◽  
Short Text ◽  
Fine Grained ◽  
Syntactic Information ◽  
Text Information

Abstract Aspect level sentiment analysis belongs to fine-grained sentiment analysis, w hich has caused extensive research in academic circles in recent years. For this task, th e recurrent neural network (RNN) model is usually used for feature extraction, but the model cannot effectively obtain the structural information of the text. Recent studies h ave begun to use the graph convolutional network (GCN) to model the syntactic depen dency tree of the text to solve this problem. For short text data, the text information is not enough to accurately determine the emotional polarity of the aspect words, and the knowledge graph is not effectively used as external knowledge that can enrich the sem antic information. In order to solve the above problems, this paper proposes a graph co nvolutional neural network (GCN) model that can process syntactic information, know ledge graphs and text semantic information. The model works on the “syntax-knowled ge” graph to extract syntactic information and common sense information at the same t ime. Compared with the latest model, the model in this paper can effectively improve t he accuracy of aspect-level sentiment classification on two datasets.

scholarly journals Network Embedding via a Bi-Mode and Deep Neural Network Model

2017 ◽  
Author(s):  
Yang Fang ◽  
Xiang Zhao ◽  
Zhen Tan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Semantic Information ◽  
Dimensional Space ◽  
Relation Extraction ◽  
Network Embedding ◽  
Structure Information ◽  
Second Mode ◽  
Real World Datasets ◽  
Low Dimensional

Network Embedding (NE) is an important method to learn the representations of network via a low-dimensional space. Conventional NE models focus on capturing the structure information and semantic information of vertices while neglecting such information for edges. In this work, we propose a novel NE model named BimoNet to capture both the structure and semantic information of edges. BimoNet is composed of two parts, i.e., the bi-mode embedding part and the deep neural network part. For bi-mode embedding part, the first mode named add-mode is used to express the entity-shared features of edges and the second mode named subtract-mode is employed to represent the entity-specific features of edges. These features actually reflect the semantic information. For deep neural network part, we firstly regard the edges in a network as nodes, and the vertices as links, which will not change the overall structure of the whole network. Then we take the nodes' adjacent matrix as the input of the deep neural network as it can obtain similar representations for nodes with similar structure. Afterwards, by jointly optimizing the objective function of these two parts, BimoNet could preserve both the semantic and structure information of edges. In experiments, we evaluate BimoNet on three real-world datasets and task of relation extraction, and BimoNet is demonstrated to outperform state-of-the-art baseline models consistently and significantly.

Sign in / Sign up

Export Citation Format

Share Document