-
Chapter and Conference Paper
GOS-IL: A Generalized Over-Sampling Based Online Imbalanced Learning Framework
Online imbalanced learning has two important characteristics: samples of one class (minority class) are under-represented in the data set and samples come to the learner online incrementally. Such a data set m...
-
Chapter and Conference Paper
ProWSyn: Proximity Weighted Synthetic Oversampling Technique for Imbalanced Data Set Learning
An imbalanced data set creates severe problems for the classifier as number of samples of one class (majority) is much higher than the other class (minority). Synthetic oversampling methods address this proble...
-
Chapter and Conference Paper
Harnessing Chaotic Activation Functions in Training Neural Network
We propose‘harnessed Chaotic Activation Functions’ (HCAF) to compute final activation of a neural network. That is biologically plausible to connect with neuron. Multilayer feed-forward neural networks are tra...
-
Chapter and Conference Paper
iRov: A Robot Platform for Active Vision Research and as Education Tool
This paper introduces an autonomous camera-equipped robot platform for active vision research and as an education tool. Due to recent progress in electronics and computing power, in control and agent technolog...
-
Chapter and Conference Paper
Artificial Bee Colony Algorithm with Improved Explorations for Numerical Function Optimization
A major problem with Artificial Bee Colony (ABC) algorithm is its premature convergence to local optima, which originates from lack of explorative search capability of the algorithm. This paper introduces ABC ...
-
Chapter and Conference Paper
A Novel Synthetic Minority Oversampling Technique for Imbalanced Data Set Learning
Imbalanced data sets contain an unequal distribution of data samples among the classes and pose a challenge to the learning algorithms as it becomes hard to learn the minority class concepts. Synthetic oversam...
-
Chapter and Conference Paper
Real-Time Hand Gesture Recognition Using Complex-Valued Neural Network (CVNN)
Computer vision system is one of the newest approaches for human computer interaction. Recently, the direct use of our hands as natural input devices has shown promising progress. Toward this progress, we intr...
-
Chapter and Conference Paper
Wirtinger Calculus Based Gradient Descent and Levenberg-Marquardt Learning Algorithms in Complex-Valued Neural Networks
Complex-valued neural networks (CVNNs) bring in nonholomorphic functions in two ways: (i) through their loss functions and (ii) the widely used activation functions. The derivatives of such functions are defin...
-
Chapter and Conference Paper
A Novel Hierarchical Constructive BackPropagation with Memory for Teaching a Robot the Names of Things
In recent years, there has been a growing attention to develop a Human-like Robot controller that hopes to move the robots closer to face real world applications. Several approaches have been proposed to suppo...
-
Chapter and Conference Paper
Vision-Motor Abstraction toward Robot Cognition
Based on indications from neuroscience and psychology, both perception and action can be internally simulated in organisms by activating sensory and/or motor areas in the brain without actual sensory input and...
-
Chapter and Conference Paper
Involving New Local Search in Hybrid Genetic Algorithm for Feature Selection
This paper presents a new hybrid genetic algorithm (HGA) for feature selection (FS) called as HGAFS. HGAFS incorporates a new local search operation that is devised and embedded in HGA to fine-tune the search ...
-
Chapter and Conference Paper
An Efficient Feature Selection Using Ant Colony Optimization Algorithm
This paper presents an efficient feature selection algorithm by utilizing the strategy of ant colony optimization, called as ACOFS. Initially, ACOFS uses a modified framework to guide the ants in the right dir...
-
Chapter and Conference Paper
A New Dynamic Edge Detection toward Better Human-Robot Interaction
Robot’s vision plays a significant role in human-robot interaction, e.g., face recognition, expression understanding, motion tracking, etc. Building a strong vision system for the robot, therefore, is one of t...
-
Chapter and Conference Paper
Diversity-Based Feature Selection from Neural Network with Low Computational Cost
This paper presents a new approach to identify the activity of input attributes efficiently in the wrapper model of feature selection. The relevant features are selected by the diversity among the inputs of th...
-
Chapter and Conference Paper
A New Constructive Algorithm for Designing and Training Artificial Neural Networks
This paper presents a new constructive algorithm, called problem dependent constructive algorithm (PDCA), for designing and training artificial neural networks (ANNs). Unlike most previous studies, PDCA puts e...
-
Chapter and Conference Paper
A Novel Algorithm for Associative Classification
Associative classifiers have been the subject of intense research for the last few years. Experiments have shown that they generally result in higher accuracy than decision tree classifiers. In this paper, we ...
-
Chapter and Conference Paper
Feature Subset Selection Using Constructive Neural Nets with Minimal Computation by Measuring Contribution
In this paper we propose a new approach to select feature subset based on contribution of input attributes in a three-layered feedforward neural network (NN). Three techniques: constructive, contribution, and ...
-
Chapter and Conference Paper
An Automatic Speaker Recognition System
Speaker Recognition is the process of identifying a speaker by analyzing spectral shape of the voice signal. This is done by extracting & matching the feature of voice signal. Mel-frequency Cepstrum Co-efficie...
-
Chapter and Conference Paper
A New Adaptive Strategy for Pruning and Adding Hidden Neurons during Training Artificial Neural Networks
This paper presents a new strategy in designing artificial neural networks. We call this strategy as adaptive merging and growing strategy (AMGS). Unlike most previous strategies on designing ANNs, AMGS puts emph...
-
Chapter and Conference Paper
Neural Network Ensemble Training by Sequential Interaction
Neural network ensemble (NNE) has been shown to outperform single neural network (NN) in terms of generalization ability. The performance of NNE is therefore depends on well diversity among component NNs. Popu...