Remote Sensing Image Features Estimating Model Based onRobust Statistical Theory and Its Application

Multi-objective optimization sampling based on Pareto optimality for soil mapping

A model-based framework of classification error rate estimation is proposed for speech and speaker recognition. It aims at predicting the run-time performance of a hidden Markov model (HMM) based recognition system for a given task vocabulary and grammar without the need of running recognition experiments using a separate set of testing samples. This is highly desirable both in theory and in practice. However, the error rate expression in HMM-based speech recognition systems has no closed form solution due to the complexity of the multi-class comparison process and the need for dynamic time warping to handle various speech patterns. To alleviate the difficulty, we propose a one-dimensional model-based misclassification measure to evaluate the distance between a particular model of interest and a combination of many of its competing models. The error rate for a class characterized by the HMM is then the value of a smoothed zero-one error function given the misclassification measure. The overall error rate of the task vocabulary could then be computed as a function of all the available class error rates. The key here is to evaluate the misclassification measure in terms of the parameters of environmental-matched models without running recognition experiments, where the models are adapted by very limited data that could be just the testing utterance itself. In this paper, we show how the misclassification measure could be approximated by first computing the distance between two mixture Gaussian densities, then between two HMMs with mixture Gaussian state observation densities and finally between two sequences of HMMs. The misclassification measure is then converted into classification error rate. When comparing the error rate obtained in running actual experiments and that of the new framework, the proposed algorithm accurately estimates the classification error rate for many types of speech and speaker recognition problems. Based on the same framework, it is also demonstrated that the error rate of a recognition system in a noisy environment could also be predicted.

Hierarchical GAN-Tree and Bi-Directional Capsules for multi-label image classification

We formulate face localization as a maximum a posteriori probability (MAP) problem of finding the best estimation of human face configuration in a given image. The a prior distribution for intrinsic face configuration is defined by active shape model (ASM). The likelihood model for local facial features is parameterized as mixture of Gaussians in feature space. A hierarchical CONDENSATION framework is then proposed to estimate the face configuration parameter. In order to improve the discriminative power of likelihood distribution in feature space, a new feature subspace, Fisher boosting feature space, is proposed and compared against PCA subspace and biased PCA subspace. Experiments show that, Fisher boosting algorithm can generate strong classifier with less number of weaker classifiers comparing to conventional Adaboosting algorithm as illustrated in a toy problem, that the face localization with Fisher boosting feature subspace outperforms that with PCA feature subspaces in localization accuracy and convergence rate, and that the design of hierarchical CONDENSATION framework alleviates the local minima problem which is frequently encountered by previous ASM optimization algorithms.

A hierarchical naive Bayesian network classifier embedded GMM for textural image

We present a mixture density based approach to invariant image object recognition. We start our experiments using Gaussian mixture densities within a Bayesian classifier. Invariance to affine transformations is achieved by replacing the Euclidean distance with SIMARD's tangent distance. We propose an approach to estimating covariance matrices with respect to image invariances as well as a new classifier combination scheme, called the virtual test sample method. On the US Postal Service handwritten digits recognition task (USPS), we obtain an excellent classification error rate of 2.7%, using the original USPS training and test sets.

The Ensemble Kalman Filter (EnKF) is derived under the assumption of Gaussian probability distributions. Thus, the successful application of the EnKF when conditioning to dynamic data depends on how well the stochastic reservoir state can be approximated by a Gaussian distribution. For facies models, the distribution becomes non-Gaussian and multi-modal, and the EnKF fails to preserve the qualitative geological structure. To apply the EnKF with models where the Gaussian approximation fails, we propose to map the ensemble to a higher dimensional feature space before the analysis step. By careful selection of the mapping, moments of arbitrary order in the canonical reservoir parameterization can be embedded in the 1st and 2nd order moments in the feature space parametrization. As a result, the parameterization in the feature space might be better approximated by a Gaussian distribution. However, the mapping from the canonical parameterization to the feature space parameterization does not have an inverse. Thus, finding the analyzed ensemble of canonical states from the analyzed ensemble represented in the feature space is an inverse problem. By using the kernel trick, the mapping to the feature space is never explicitly computed, and we solve the inverse problem efficiently by minimizing a cost function based on the feature space distance. As a result, the computational efficiency of the EnKF is retained, and the methodology is applicable for large scale reservoir models. The proposed methodology is evaluated as an alternative to other approaches for estimation of facies with the EnKF, such as the truncated pluri-Gaussian approach. Results from a field case are shown.

Thin-plate spline fitting is often applied to fitting smooth surfaces to a collection of data. However, discontinuities in the data are smoothed by this technique. This occurs because of several underlying assumptions of spline fitting that do not hold when discontinuities are present. The theory of robust statistics can be used to deal with these outliers. In this paper, we present one way to apply the theory of robust statistics to the problem of discontinuous surface fitting.

PulseID: Multi-scale photoplethysmographic identification using a deep convolutional neural network

Although rare in the sound recognition literature, previous work using features derived from a sparse temporal representation has led to some success [8, 2, 9]. A great advantage of deriving features from a temporal representation is that such an approach does not face the trade-off problem between time and frequency resolution. Here, we present a biologically inspired two-step process for audio classification: In the first step, efficient basis functions are learned in an unsupervised manner [12] on mixtures of percussion sounds (drum phrases). In the second step, features are extracted by using the learned basis functions to decompose percussion sounds (base drum, snare drum, hi-hat) with matching pursuit [7]. The classification accuracy in a 3-class database transfer task is 91.5% as opposed to 70.7% when using MFCC features. Further, we show that a MP-feature representation preserves sound similarity to a greater extent than MFCC-features, i.e. an artificial mixture of two sounds of equal energy normally lies in the middle between the two single sound distributions in feature space. An MP-representation thus inherently contains a similarity measure between different sounds.

The widely deployment of infrastructure and wireless interfaces increases industrial IoT (IIoT) vulnerability to network intrusions, highlighting the requirements for robust network intrusion detection systems (NIDSs). Although deep learning (DL) provides a promising solution for NIDSs, it remains susceptible to adversarial attacks as minor input perturbations can lead to major misclassifications. In this paper, we propose a packet-level adversarial traffic generation (PATG) approach for attacking NIDSs in IIoT, which not only aligns with domain constraints but also evades various DL-based NIDSs. Particularly, we introduce a reversible abstract traffic representation to ensure that the original traffic can be effectively modified while preserving its functionality. We propose a packet-level generative adversarial networks to craft adversarial traffic by learning benign data distribution in feature space and simulating evasion behaviors, which escapes the DL-based NIDSs. We further design two defense schemes to enhance system resilience against proposed adversarial attacks. We evaluate PATG on nine state-of-the-art DL-based NIDSs in the Kitsune and CICIoT23 datasets. Experimental results demonstrate that PATG can achieve a maximum evasion increase rate of 99% with cost-effective execution, while the defense methods significantly mitigate the impact of the adversarial attacks.

We study the use of Support Vector Machines (SVM) for detecting the occurrence of articulatory features in speech audio data and using the information contained in the detector outputs to improve phone and speech recognition. Our expectation is that an SVM should be able to appropriately model the separation of the classes which may have complex distributions in feature space. We show that performance improves markedly when using discriminatively trained speaker dependent parameters for the SVM inputs, and compares quite well to results in the literature using other classifiers, namely Artificial Neural Networks (ANN). Further, we show that the resulting detector outputs can be successfully integrated into a state of the art speech recognition system, with consequent performance gains. Notably, we test our system on English broadcast news data from dev04f.

We present a texture network called Deep Encoding Pooling Network (DEP) for the task of ground terrain recognition. Recognition of ground terrain is an important task in establishing robot or vehicular control parameters, as well as for localization within an outdoor environment. The architecture of DEP integrates orderless texture details and local spatial information and the performance of DEP surpasses state-of-the-art methods for this task. The GTOS database (comprised of over 30,000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition. For evaluation under realistic conditions, we use test images that are not from the existing GTOS dataset, but are instead from hand-held mobile phone videos of similar terrain. This new evaluation dataset, GTOS-mobile, consists of 81 videos of 31 classes of ground terrain such as grass, gravel, asphalt and sand. The resultant network shows excellent performance not only for GTOS-mobile, but also for more general databases (MINC and DTD). Leveraging the discriminant features learned from this network, we build a new texture manifold called DEP-manifold. We learn a parametric distribution in feature space in a fully supervised manner, which gives the distance relationship among classes and provides a means to implicitly represent ambiguous class boundaries. The source code and database are publicly available.

Many of the near-duplicate (ND) image detection methods involve a greater number of interest points (IPs) and large dimensions of the feature descriptors requiring huge computations and are unsuitable for large image databases. They may fail to detect NDs if the query and images in the database contain sparse IPs due to low entropy. Besides, the k-means algorithm used for the quantization of visual words may land at a sub-optimal minimum for descriptors because of their distance distribution in feature space. This article presents a new ND image detection method, which uniformly distributes the IPs over low and high entropy regions, reduces the dimension of feature descriptors using discrete wavelet transform (DWT) and employs Seagull Optimization algorithm (SOA) for optimally forming the visual words. It examines proposed method performs on image databases of various sizes and shows that the developed method is more reliable and computationally efficient than the alternatives.

City designs in Iran have used the hierarchy principle in all elements of the cities from the components to the whole. The physical cells of tissues in an urban area are clearly related. However, in the development of cities, traces of the network of space communications to the old city centre remain. Instead of composition streets, squares and communication between, the networks contain filled rows with independent buildings. The purpose of this article is to recover the specific relationships between elements of the city and the urban hierarchy with regard to morphological aspects. In this study, urban tissue and typology are used to assess the pattern of urban streets, blocks, squares and islands. The typology of urban tissue based on evaluation of the mentioned patterns is established through field studies, aerial photos and maps of separated lands. We chose the city of Boshrooyeh in eastern Iran as the case study. The historic city core sector has been evaluated in terms of physical characteristics, which provide the morphological typology of the urban tissue. After analysis, data can be investigated in the presence or absence of access hierarchy in different historical periods of the city. The purpose of identifying the morphological typology of the city’s historic fabric is to help us determine the hierarchical order and coherence of the city. The result of this study shows the rapid development of the city, including widening streets, and destruction of the urban form (Main Street and Square). These incidents have led to loss of infrastructure, urban identity, and disorganisation in the urban hierarchy.