Feature Selection for Hyperspectral Images using Single-Layer Neural Networks

One of the most important threats to today’s civilization is terrorism. Terrorism not only disturbs the law and order situations in a society but also affects the quality of lives of humans and makes them suppressed physically and emotionally and deprives them of enjoying life. The more the civilizations have advanced, the more the people are working towards exploring different mechanisms to protect the mankind from terrorism. Different techniques have been used as counterterrorism to protect the lives of individuals in society and to improve the quality of life in general. Machine learning methods have been recently explored to develop techniques for counterterrorism based on artificial intelligence (AI). Since deep learning has recently gained more popularity in machine learning domain, in this paper, these techniques are explored to understand the behavior of terrorist activities. Five different models based on deep neural network (DNN) are created to understand the behavior of terrorist activities such as is the attack going to be successful or not? Or whether the attack is going to be suicide or not? Or what type of weapon is going to be used in the attack? Or what type of attack is going to be carried out? Or what region is going to be attacked? The models are implemented in single-layer neural network (NN), five-layer DNN, and three traditional machine learning algorithms, i.e., logistic regression, SVM, and Naïve Bayes. The performance of the DNN is compared with NN and the three machine learning algorithms, and it is demonstrated that the performance in DNN is more than 95% in terms of accuracy, precision, recall, and F1-Score, while ANN and traditional machine learning algorithms have achieved a maximum of 83% accuracy. This concludes that DNN is a suitable model to be used for predicting the behavior of terrorist activities. Our experiments also demonstrate that the dataset for terrorist activities is big data; therefore, a DNN is a suitable model to process big data and understand the underlying patterns in the dataset.

Deep neural network has been extensively applied to hyperspectral image (HSI) classification recently. However, its success is greatly attributed to numerous labeled samples, whose acquisition costs a large amount of time and money. In order to improve the classification performance while reducing the labeling cost, this article presents an active deep learning approach for HSI classification, which integrates both active learning and deep learning into a unified framework. First, we train a convolutional neural network (CNN) with a limited number of labeled pixels. Next, we actively select the most informative pixels from the candidate pool for labeling. Then, the CNN is fine-tuned with the new training set constructed by incorporating the newly labeled pixels. This step together with the previous step is iteratively conducted. Finally, Markov random field (MRF) is utilized to enforce class label smoothness to further boost the classification performance. Compared with the other state-of-the-art traditional and deep learning-based HSI classification methods, our proposed approach achieves better performance on three benchmark HSI data sets with significantly fewer labeled samples.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

BackgroundRecently, successful applications of the discrete wavelet transform have been reported in brain interface (BI) systems with one or two EEG channels. For a multi-channel BI system, however, the high dimensionality of the generated wavelet features space poses a challenging problem.MethodsIn this paper, a feature selection method that effectively reduces the dimensionality of the feature space of a multi-channel, self-paced BI system is proposed. The proposed method uses a two-stage feature selection scheme to select the most suitable movement-related potential features from the feature space. The first stage employs mutual information to filter out the least discriminant features, resulting in a reduced feature space. Then a genetic algorithm is applied to the reduced feature space to further reduce its dimensionality and select the best set of features.ResultsAn offline analysis of the EEG signals (18 bipolar EEG channels) of four able-bodied subjects showed that the proposed method acquires low false positive rates at a reasonably high true positive rate. The results also show that features selected from different channels varied considerably from one subject to another.ConclusionThe proposed hybrid method effectively reduces the high dimensionality of the feature space. The variability in features among subjects indicates that a user-customized BI system needs to be developed for individual users.

Cardiotocography (CTG) is a worldwide method used for recording fetal heart rate and uterine contractions during pregnancy and delivery. The consistent visual assessment of the CTG is not only time consuming but also requires expertise and clinical knowledge of the obstetricians. The inconsistency in visual evaluation can be eliminated by developing clinical decision support systems. During last few decades various data mining and machine learning techniques have been proposed for developing such systems. In present study, bagging approach in combination with three traditional decision trees algorithms (random forest, Reduced Error Pruning Tree (REPTree) and J48) has been applied to identify normal and pathological fetal state using CTG data. Studies show that decision trees algorithms and bagging have separately shown tremendous improvements in the classification of healthy and pathological subjects in medical domain. The parameters of classifiers were optimized before applying on the data sets. The ten folds cross validation is used for examining the robust of the classifiers. The degree of separation was quantified using Precision, Recall and F-Measure. At first full feature space have been analyzed using proposed bagging based decision trees algorithms. Then by using correlation feature selection - subset evaluation (cfs) method, a reduced feature space has been obtained and analyzed using proposed method. The overall classification accuracy of more than 90% has been obtained by the classifiers on the test set when full feature space is used. For all three performance measures, values greater than 0.90 has been achieved with full and reduced feature space. The proposed methodology showed better classification in both full and reduced feature space scenarios.

Land cover and its dynamic information is the basis for characterizing surface conditions, supporting land resource management and optimization, and assessing the impacts of climate change and human activities. In land cover information extraction, the traditional convolutional neural network (CNN) method has several problems, such as the inability to be applied to multispectral and hyperspectral satellite imagery, the weak generalization ability of the model and the difficulty of automating the construction of a training database. To solve these problems, this study proposes a new type of deep convolutional neural network based on Landsat-8 Operational Land Imager (OLI) imagery. The network integrates cascaded cross-channel parametric pooling and average pooling layer, applies a hierarchical sampling strategy to realize the automatic construction of the training dataset, determines the technical scheme of model-related parameters, and finally performs the automatic classification of remote sensing images. This study used the new type of deep convolutional neural network to extract land cover information from Qinhuangdao City, Hebei Province, and compared the experimental results with those obtained by traditional methods. The results show that: (1) The proposed deep convolutional neural network (DCNN) model can automatically construct the training dataset and classify images. This model performs the classification of multispectral and hyperspectral satellite images using deep neural networks, which improves the generalization ability of the model and simplifies the application of the model. (2) The proposed DCNN model provides the best classification results in the Qinhuangdao area. The overall accuracy of the land cover data obtained is 82.0%, and the kappa coefficient is 0.76. The overall accuracy is improved by 5% and 14% compared to the support vector machine method and the maximum likelihood classification method, respectively.

Survey on Deep Neural Networks in Speech and Vision Systems

Chapter 5 - Training multilayer neural networks

Development in the field of computer-aided learning and testing have stimulated the progress of novel and efficient knowledge-based expert systems that have shown hopeful outcomes in a broad variety of practical applications. In particular, deep learning techniques have been extensively carried out to identify remote sensed data obtained by the instruments of Earth observation. Hyperspectral imaging (HSI) is an evolving area in the study of remotely sensed data due to the huge volume of information found in these images, which enables better classification and processing of the Earth’s surface by integrating ample of spatial and spectral features. Nevertheless, because of the high-dimensional data and restricted training samples available, HSI presents some crucial challenges for classification of supervised methods. In particular, it addresses the problems of spectral and spatial resolution, volume of data, and model conversion from multimedia images to hyperspectral data. Various deep learning-based architectures are currently being established to solve these limitations, showing significant results in the analysis of hyperspectral data. In this paper, we deal primarily with the hyperspectral datasets, the dimensionality curse problem, and methods for classifying those datasets using some deep neural networks (DNN), especially convolutional neural networks (CNN). We provide a comparative analysis of various dimensionality reduction (DR) and classification techniques used for finding accuracies based on the datasets used. We also explore certain hyperspectral imaging applications along with some of the research axes.

The data mining methods have been extensively used in the process of decision making. The popularity of data mining methods is due to availability of high speed algorithms, processing and storage power of computers. The effective use of data mining methods help in mining datasets and taking better decisions. The data need to be preprocessed before applying data mining methods. Some datasets require little preparation like dealing with missing and redundant instances while some high-dimensional datasets require strong processing like dimensionality reduction. One of the techniques used for dimensionality reduction is feature selection. This study uses graph based centrality measure for feature selection. Graph based centrality measures are used for ranking features which is used for removing irrelevant attributes. After comparison of results with other approaches, it has been found that the proposed approach results in reduction of feature space without compromising accuracy. The results also shows that proposed approach performs better than some other feature selection approaches not only in terms of accuracy but also on the basis of larger reduction in feature space.

In this study, the deep multi-layered group method of data handling (GMDH)-type neural network algorithm using revised heuristic self-organization method is proposed and applied to medical image diagnosis of liver cancer. The deep GMDH-type neural network can automatically organize the deep neural network architecture which has many hidden layers. The structural parameters such as the number of hidden layers, the number of neurons in hidden layers and useful input variables are automatically selected to minimize prediction error criterion defined as Akaike’s information criterion (AIC) or prediction sum of squares (PSS). The architecture of the deep neural network is automatically organized using the revised heuristic self-organization method which is a type of the evolutionary computation. This new neural network algorithm is applied to the medical image diagnosis of the liver cancer and the recognition results are compared with the conventional 3-layered sigmoid function neural network.

Deep neural networks are a branch in machine learning that has seen a meteoric rise in popularity due to its powerful abilities to represent and model high-level abstractions in highly complex data. One area in deep neural networks that are ripe for exploration is neural connectivity formation. A pivotal study on the brain tissue of rats found that synaptic formation for specific functional connectivity in neocortical neural microcircuits can be surprisingly well modeled and predicted as a random formation. Motivated by this intriguing finding, we introduce the concept of StochasticNet where deep neural networks are formed via stochastic connectivity between neurons. As a result, any type of deep neural networks can be formed as a StochasticNet by allowing the neuron connectivity to be stochastic. Stochastic synaptic formations in a deep neural network architecture can allow for efficient utilization of neurons for performing specific tasks. To evaluate the feasibility of such a deep neural network architecture, we train a StochasticNet using four different image datasets (CIFAR-10, MNIST, SVHN, and STL-10). Experimental results show that a StochasticNet using less than half the number of neural connections as a conventional deep neural network achieves comparable accuracy and reduces overfitting on the CIFAR-10, MNIST, and SVHN data sets. Interestingly, StochasticNet with less than half the number of neural connections, achieved a higher accuracy (relative improvement in test error rate of $\sim 6$ % compared to ConvNet) on the STL-10 data set than a conventional deep neural network. Finally, the StochasticNets have faster operational speeds while achieving better or similar accuracy performances.

Maximum relevancy maximum complementary feature selection for multi-sensor activity recognition

Modelling of soil moisture retention curve using machine learning techniques: Artificial and deep neural networks vs support vector regression models

This paper presents the development of several efficient learning algorithms for neural networks (ELEANNE). The ELEANNE 1 and ELEANNE 2 are two recursive least-squares learning algorithms, proposed for training single-layered neural networks with analog output. This paper also proposes a new optimization strategy for training single-layered neural networks, which provides the basis for the development of a variety of efficient learning algorithms. This optimization strategy is the source of the ELEANNE 3, a second-order learning algorithm for training single-layered neural networks with binary output. A simplified version of this algorithm, called ELEANNE 4, is also derived on the basis of some simplifying but reasonable assumptions. The two algorithms developed for single-layered neural networks provide the basis for the derivation of ELEANNE 5 and ELEANNE 6, which are proposed for training multilayered neural networks with binary output. The ELEANNE 7 is an efficient algorithm developed for training multilayered neural networks with either binary or analog output. >