34 Result(s)
within
Chapter
**ngzhong Wang
-
Chapter and Conference Paper
Time Series Processing Scheme Based on Deep Learning and Spatio-temporal Network Modeling
In order to study how massive data with periodic and tidal performance influences identification and processing in present network, this paper proposes a data-processing method combined with deep learning algo...
-
Chapter and Conference Paper
Context Matters: Cross-Domain Cell Detection in Histopathology Images via Contextual Regularization
Deep learning-based cell detectors have shown promise in automating cell detection in histopathology images, which can aid in cancer diagnosis and prognosis. Nevertheless, the color variation in stain appearan...
-
Chapter and Conference Paper
Patient Mortality Prediction Based on Two-Layer Attention Neural Network
With the development of medical informatization, electronic medical records are important in hospital information systems, and their use for patient mortality prediction can contribute to further improvement o...
-
Chapter and Conference Paper
The Application of GIS Techniques in Distribution of Soil Trace Elements in Tropical Area: A Case Study of Zinc
Taking Hainan Island as the object, this study adopted field investigation and spatial analysis methods to reveal the abundance and deficiency rules of available zinc in agricultural soil on the basis of clari...
-
Chapter and Conference Paper
Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN
In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, we present a medical practical degradation model t...
-
Chapter and Conference Paper
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-Ray Images of Multiple Body Parts
While self-supervised learning (SSL) algorithms have been widely used to pre-train deep models, few efforts [11] have been done to improve representation learning of X-ray image analysis with SSL pre-trained mode...
-
Chapter and Conference Paper
Experimental Study on Uniaxial Strain Cyclic Behavior of GS-20Mn5
Due to the common discontinuity of the structure and non-uniform load, local high stress phenomenon tends to appear in the mechanical structure under repeated loading, and even local small plastic deformation ...
-
Chapter and Conference Paper
Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
Image super-resolution is important in many fields, such as surveillance and remote sensing. However, infrared (IR) images normally have low resolution since the optical equipment is relatively expensive. Rece...
-
Chapter and Conference Paper
Off-Policy Differentiable Logic Reinforcement Learning
In this paper, we proposed an Off-Policy Differentiable Logic Reinforcement Learning (OPDLRL) framework to inherit the benefits of interpretability and generalization ability in Differentiable Inductive Logic ...
-
Chapter and Conference Paper
Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
A wide range of image captioning models has been developed, achieving significant improvement based on popular metrics, such as BLEU, CIDEr, and SPICE. However, although the generated captions can accurately d...
-
Chapter and Conference Paper
Development Strategy of E-Commerce Network Marketing Based on New Media Marketing Mode
The new media marketing is to implement the enterprise’s soft-penetration business strategy in the form of new media. New media are used to express and disseminate ideas, ideas, and concepts that enable consum...
-
Chapter and Conference Paper
Speech Training System for Hearing Impaired Individuals Based on Automatic Lip-Reading Recognition
Using automatic lip recognition technology to promote social interaction and integration of hearing impaired individuals and dysphonic people is one of promising applications of artificial intelligence in heal...
-
Chapter
Dopaminergic Neuron-Related Stem Cells
Midbrain dopaminergic (mDA) neurons have been an intense area of research for many years, in part because progressive loss of mDA neurons causes the second most common neurodegenerative disease, Parkinson’s di...
-
Chapter and Conference Paper
Analysis and Design of Key Parameters in Intelligent System of Lime Rotary Kiln
This paper establishes a three-dimensional model based on the structure of the existing preheater, and simulates the preheater, optimizes the corresponding structure according to the analogue analysis structur...
-
Chapter and Conference Paper
Study on Key Design Parameters of Calcinations System in Rotary Lime Kiln Based on Computer Simulation
At present, the lime technology of rotary kiln in our country lacks basic research. There is no systematic study on the influence of key design conditions such as raw materials and fuel on the design parameter...
-
Chapter and Conference Paper
Gated Hierarchical Attention for Image Captioning
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly impr...
-
Chapter and Conference Paper
Inferring Continuous Latent Preference on Transition Intervals for Next Point-of-Interest Recommendation
Temporal information plays an important role in Point-of-Interest (POI) recommendations. Most existing studies model the temporal influence by utilizing the observed check-in time stamps explicitly. With the c...
-
Chapter
Genetics of Suicidal Behaviour
Suicide is a complex and multifactorial disorder. Two important risk factors, genetic and environment, contribute significantly to the psychopathology and aetiology of suicidal behaviour. In the last two decad...
-
Chapter and Conference Paper
Face Recognition Based on Deep Belief Network Combined with Center-Symmetric Local Binary Pattern
Human face recognition performances usually drops heavily due to pose variation and other factors. The representative deep learning method Deep Belief Network (DBN) has been proven to be an effective method to...
-
Chapter and Conference Paper
Privacy-Preserving Anomaly Detection Across Multi-domain for Software Defined Networks
Software Defined Network (SDN) separates control plane from data plane and provides programmability which adds rich function for anomaly detection. In this case, every organization can manage their own network...
