16 Result(s)
-
Chapter and Conference Paper
APNet2: High-Quality and High-Efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra
In our previous work, we have proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then r...
-
Chapter and Conference Paper
Damage Information of Fiber Reinforced Concrete Based on Digital Image 3D-DIC Technology
The meso-scale study can reflect the failure nature of fiber reinforced concrete, and the meso-level analysis can be used as the basis for the study of macro-mechanical response of concrete under load. With th...
-
Chapter and Conference Paper
A Biogeography-Based Memetic Algorithm for Job-Shop Scheduling
Job shop scheduling problem (JSP) is a well-known combinatorial optimization problem of practical importance, but existing evolutionary algorithms for JSP often face problems of low convergence speed and/or pr...
-
Chapter and Conference Paper
Stereo Matching Based on Density Segmentation and Non-Local Cost Aggregation
Recently, segment-tree based Non-Local cost aggregation algorithm, which can provide extremely low computational complexity and outstanding performance, has been proposed for stereo matching. The segment-tree ...
-
Chapter and Conference Paper
Contractive ML-ELM for Invariance Robust Feature Extraction
Extreme Learning Machine (ELM), a single hidden layer feedforward neural networks works efficiently in many areas such as machine learning, pattern recognition, natural language processing, et al. due to its p...
-
Chapter and Conference Paper
Research on Visual Weld Trace Detection Method Based on Invariant Moment Features
A visual weld trace detection method based on invariant moment features is proposed in this paper for cosmetic welding inspection. The proposed method can not only overcome the absence of distortion in structu...
-
Chapter and Conference Paper
A Flocculation and Deposit Model of Asphaltene in Porous Media for Damage Evaluation
The flocculation and deposit of asphaltene in porous media is concerned all the time by researchers home and overseas; because of its complexity, the study of testing method, flocculation and deposit theory is a ...
-
Chapter and Conference Paper
Adaptive Dynamic Surface Control of a Class of Nonlinear Systems with Unknown Duhem Hysteresis
In this paper, the tracking problem for a class of uncertain perturbed strict-feedback nonlinear systems with unknown Duhem hysteresis input is investigated. Different with the conventional nonlinear systems, ...
-
Chapter and Conference Paper
Brushless DC Motor Speed Fuzzy Adaptive Control System
For brushless DC motor speed control accuracy is not high, this paper adapts adaptive fuzzy PID control method to control rotation speed and the current double speed closed-loop speed control systems, combine ...
-
Chapter and Conference Paper
Non-intrusive Personalized Mental Workload Evaluation for Exercise Intensity Measure
Non-intrusive measures of mental workload signals are desirable, because they minimize artificially introduced noise, and can be more accurate. A new approach for non-intrusive personalized mental workload eva...
-
Chapter and Conference Paper
When does Co-training Work in Real Data?
Co-training, a paradigm of semi-supervised learning, may alleviate effectively the data scarcity problem (i.e., the lack of labeled examples) in supervised learning. The standard two-view co-training requires ...
-
Chapter and Conference Paper
Bark Classification Based on Contourlet Filter Features Using RBPNN
This paper proposed a new method of extracting texture features based on contourlet domain in RGB color space. In addition, the application of these features for bark classification applying radial basis proba...
-
Chapter and Conference Paper
Bark Classification Based on Gabor Filter Features Using RBPNN Neural Network
This paper proposed a new method of extracting texture features based on Gabor wavelet. In addition, the application of these features for bark classification applying radial basis probabilistic network (RBPNN...
-
Chapter and Conference Paper
The Design of a Fuzzy-Neural Network for Ship Collision Avoidance
A fuzzy-neural network for ship collision avoidance where ships are in sight of one another is proposed in this article. There are three subsets: the subset of classifying ship encounter situations and collisi...
-
Chapter and Conference Paper
Autocontrol of Performance Measurement for RhombShape Achromatic Phase Retarder
Achromatic retarder is an important optical device. Because of its important applied value, modern polarization technology and optical modulation demand high precision for the design and measurement of achroma...
-
Chapter and Conference Paper
Noisy Speech Recognition Performance of Discriminative HMMs
Discriminatively trained HMMs are investigated in both clean and noisy environments in this study. First, a recognition error is defined at different levels including string, word, phone and acoustics. A high ...
