-
Chapter and Conference Paper
Global Exponential Stability of Recurrent Neural Networks with Time-Dependent Switching Dynamics
In this paper, the switching dynamics of recurrent neural networks are studied. Sufficient conditions on global exponential stability with an arbitrary switching law or a dwell time switching law and the estim...
-
Chapter and Conference Paper
Finding Intrinsic and Extrinsic Viewing Parameters from a Single Realist Painting
In this paper we studied the geometry of a three-dimensional tableau from a single realist painting – Scott Fraser’s Three way vanitas (2006). The tableau contains a carefully chosen complex arrangement of object...
-
Chapter and Conference Paper
An Image Encryption Algorithm Based on Small Permutation Array Combining
In traditional chaotic map based image encryption algorithm, the encryption performance is determined by the permutation generating speed, and due to short periodical problem led by the finite precision effect...
-
Chapter and Conference Paper
Adaptive Backstep** Neural Control for Switched Nonlinear Stochastic System with Time-Delay Based on Extreme Learning Machine
In this paper, for a class of switched stochastic nonlinear systems with time-varying delays, the output feedback stabilization problem is addressed based on single hidden layer feed-forward network (SLFN) and...
-
Chapter and Conference Paper
Damage Pattern Recognition of Refractory Materials Based on BP Neural Network
The determination of the damage mode and the quantitative description of the damage of the clustered acoustic emission (AE) signal of the refractory materials based on the BP (back propagation) Neural Network ...
-
Chapter and Conference Paper
Displacement Prediction Model of Landslide Based on Ensemble of Extreme Learning Machine
Based on time series analysis, total accumulative displacement of landslide is divided into the trend component displacement and the periodic component displacement according to the response relation between d...
-
Chapter and Conference Paper
Distance Metric Learning-Based Conformal Predictor
In order to improve the computational efficiency of conformal predictor, distance metric learning methods were used in the algorithm. The process of learning was divided into two stages: offline learning and o...
-
Chapter and Conference Paper
Study on Landslide Deformation Prediction Based on Recurrent Neural Network under the Function of Rainfall
Landslide deformation prediction has significant practical value that can provide guidance for preventing the disaster and guarantee the safety of people’s life and property. In this paper, a method based on r...
-
Chapter and Conference Paper
Classifying Stem Cell Differentiation Images by Information Distance
The ability of stem cells holds great potential for drug discovery and cell replacement therapy. To realize this potential, effective high content screening for drug candidates is required. Analysis of images ...
-
Chapter and Conference Paper
Local Clustering Conformal Predictor for Imbalanced Data Classification
The recently developed Conformal Predictor (CP) can provide calibrated confidence for prediction which is out of the traditional predictors’ capacity. However, CP works for balanced data and fails in the case ...
-
Chapter and Conference Paper
Generalized Regression Neural Networks with K-Fold Cross-Validation for Displacement of Landslide Forecasting
This paper proposes a generalized regression neural networks (GRNNS) with \(K\) -fold cross-validation (GRNNSK) for pr...
-
Chapter and Conference Paper
A Kernel ELM Classifier for High-Resolution Remotely Sensed Imagery Based on Multiple Features
Better interpretation about the contents in high-resolution remote sensing images can be obtained by using multiple features of various types. In order to process large image data sets with high feature dimens...
-
Chapter and Conference Paper
Multi-step Predictions of Landslide Displacements Based on Echo State Network
Time series prediction theory and methods can be applied to many practical problems, such as the early warning of landslide hazard. Most already existing time series prediction methods cannot be effectively ap...
-
Chapter and Conference Paper
Semi-supervised Non-negative Local Coordinate Factorization
Non-negative matrix factorization (NMF) is a popular matrix decomposition technique that has attracted extensive attentions from data mining community. However, NMF suffers from the following deficiencies: (1)...
-
Chapter and Conference Paper
Event Detection with Convolutional Neural Networks for Forensic Investigation
Traditional approaches rely on domain expertise to acquire complicated features. Meanwhile, existing Natural Language Processing (NLP) tools and techniques are not competent to extract information from digital...
-
Chapter and Conference Paper
A Novel Recommendation Service Method Based on Cloud Model and User Personality
The number of Internet Web services has become increasingly large recently. Cloud services consumers face a critical challenge in selecting services from abundant candidates. Due to the uncertainty of Web serv...
-
Chapter and Conference Paper
Hypergraph-Based Data Reduced Scheduling Policy for Data-Intensive Workflow in Clouds
Data-intensive computing is expected to be the next-generation IT computing paradigm. Data-intensive workflows in clouds are becoming more and more popular. How to schedule data-intensive workflow efficiently ...
-
Chapter and Conference Paper
Cross-Layer Convolutional Siamese Network for Visual Tracking
In most trackers for visual tracking, Siamese network based trackers construct a pair of twin structures to learn a similarity metric between tracked object and search region to predict the position of the obj...
-
Chapter and Conference Paper
Logit Distillation via Student Diversity
Knowledge distillation (KD) is a technique of transferring the knowledge from a large teacher network to a small student network. Current KD methods either make a student mimic diverse teachers with knowledge ...
-
Chapter and Conference Paper
AAT: Non-local Networks for Sim-to-Real Adversarial Augmentation Transfer
In sim-to-real task, domain adaptation is one of the basic challenge topic as it can reduce the huge performance variation caused by domain shift. Domain adaptation can effectively transfer knowledge from a la...