scholarly journals Scatter Matrix Based Domain Adaptation for Bi-Temporal Polarimetric SAR Images

2020 ◽  
Vol 12 (4) ◽  
pp. 658
Author(s):  
Weidong Sun ◽  
Pingxiang Li ◽  
Bo Du ◽  
Jie Yang ◽  
Linlin Tian ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Principal Component ◽  
Mapping Function ◽  
Detection Methods ◽  
Scatter Matrix ◽  
Label Information ◽  
Multi Temporal ◽  
Maximum Margin Criterion ◽  
Low Dimensional ◽  
Optimal Subspace

Time series analysis (TSA) based on multi-temporal polarimetric synthetic aperture radar (PolSAR) images can deeply mine the scattering characteristics of objects in different stages and improve the interpretation effect, or help to extract the range of surface changes. However, as far as classification is concerned, it is difficult to directly generate the classification map for a new temporal image, by the use of conventional TSA or change detection methods. Once some labeled samples exist in historical temporal images, semi-supervised domain adaptation (DA) is able to use historical label information to infer the categories of pixels in the new image, which is a potential solution to the above problem. In this paper, a novel semi-supervised DA algorithm is proposed, which inherits the merits of maximum margin criterion and principal component analysis in the DA learning scenario. Using a kernel mapping function established on the statistical distribution of PolSAR data, the proposed algorithm aims to find an optimal subspace for eliminating domain influence and keeping the key information of bi-temporal images. Experiments on both UAVSAR and Radarsat-2 multi-temporal datasets show that, superior classification results with the average accuracy of about 80% can be obtained by a simple classifier trained with historical labeled samples in the learned low- dimensional subspaces.

Enhanced Parameter-Free Diversity Discriminant Preserving Projections for Face Recognition

2018 ◽  
Vol 32 (10) ◽  
pp. 1856013 ◽  
Author(s):  
Xingzhu Liang ◽  
Yu’e Lin
Keyword(s):  
Face Recognition ◽  
The Novel ◽  
Similarity Matrix ◽  
Face Database ◽  
Class Label ◽  
Data Set ◽  
Scatter Matrix ◽  
Label Information ◽  
Maximum Margin Criterion ◽  
Data Points

The manifold-based learning methods have recently drawn more and more attention in dimension reduction. In this paper, a novel manifold-based learning method named enhanced parameter-free diversity discriminant preserving projections (EPFDDPP) is presented, which effectively avoids the neighborhood parameter selection and characterizes the manifold structure well. EPFDDPP redefines the weighted matrices, the discriminating similarity matrix and the discriminating diversity matrix, respectively. The weighted matrices are computed by the cosine angle distance between two data points and take special consideration of both the local information and the class label information, which are parameterless and favorable for face recognition. After characterizing the discriminating similarity scatter matrix and the discriminating diversity scatter matrix, the novel feature extraction criterion is derived based on maximum margin criterion. Experimental results on the Wine data set, Olivetti Research Laboratory (ORL); AR (face database created by Aleix Martinez and Robert Benavente); and Pose, Illumination, and Expression (PIE) face databases show the effectiveness of the proposed method.

scholarly journals A Fuzzy Kernel Maximum Margin Criterion for Image Feature Extraction

2015 ◽  
Vol 2015 ◽  
pp. 1-13
Author(s):  
Shibin Xuan
Keyword(s):  
Feature Extraction ◽  
Principal Component ◽  
Training Sample ◽  
Computational Method ◽  
Image Feature ◽  
Kernel Principal Component Analysis ◽  
Image Feature Extraction ◽  
Scatter Matrix ◽  
Maximum Margin ◽  
Maximum Margin Criterion

Based on kernel principal component analysis, fuzzy set theory, and maximum margin criterion, a novel image feature extraction and recognition method, called fuzzy kernel maximum margin criterion (FKMMC), is proposed. In the proposed method, two new fuzzy scatter matrixes are redefined. The new fuzzy scatter matrix can reflect fully the relation between fuzzy membership degree and the offset of the training sample to subclass center. Besides, a concise reliable computational method of the fuzzy between-class scatter matrix is provided. Experimental results on four face databases (AR, extended Yale B, GTFD, and FERET) demonstrate that the proposed method outperforms other methods.

scholarly journals Numerical Valuation of American Basket Options via Partial Differential Complementarity Problems

Mathematics ◽  
2021 ◽  
Vol 9 (13) ◽  
pp. 1498
Author(s):  
Karel J. in’t Hout ◽  
Jacob Snoeijer
Keyword(s):  
Principal Component Analysis ◽  
Numerical Experiments ◽  
Complementarity Problems ◽  
Principal Component ◽  
Partial Differential ◽  
Basket Options ◽  
Basket Option ◽  
Option Values ◽  
Convergence Behaviour ◽  
Low Dimensional

We study the principal component analysis based approach introduced by Reisinger and Wittum (2007) and the comonotonic approach considered by Hanbali and Linders (2019) for the approximation of American basket option values via multidimensional partial differential complementarity problems (PDCPs). Both approximation approaches require the solution of just a limited number of low-dimensional PDCPs. It is demonstrated by ample numerical experiments that they define approximations that lie close to each other. Next, an efficient discretisation of the pertinent PDCPs is presented that leads to a favourable convergence behaviour.

scholarly journals Domain-Adversarial Training of Self-Attention-Based Networks for Land Cover Classification Using Multi-Temporal Sentinel-2 Satellite Imagery

2021 ◽  
Vol 13 (13) ◽  
pp. 2564
Author(s):  
Mauro Martini ◽  
Vittorio Mazzia ◽  
Aleem Khaliq ◽  
Marcello Chiaberge
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Domain Adaptation ◽  
Learning Approaches ◽  
Atmospheric Conditions ◽  
Practical Applications ◽  
Area Of Interest ◽  
Multi Temporal ◽  
Significant Performance ◽  
Adversarial Training

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time-consuming solution that pose strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention-based models for LC&CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

scholarly journals Separating damage from environmental effects affecting civil structures for near real-time damage detection

2017 ◽  
Vol 17 (4) ◽  
pp. 850-868 ◽  
Author(s):  
William Soo Lon Wah ◽  
Yung-Tsang Chen ◽  
Gethin Wyn Roberts ◽  
Ahmed Elamin
Keyword(s):  
Damage Detection ◽  
Real Time ◽  
Environmental Effects ◽  
Environmental Conditions ◽  
Principal Component ◽  
Detection Methods ◽  
Real Time Monitoring ◽  
Civil Structures ◽  
Data Set ◽  
Wide Range

Analyzing changes in vibration properties (e.g. natural frequencies) of structures as a result of damage has been heavily used by researchers for damage detection of civil structures. These changes, however, are not only caused by damage of the structural components, but they are also affected by the varying environmental conditions the structures are faced with, such as the temperature change, which limits the use of most damage detection methods presented in the literature that did not account for these effects. In this article, a damage detection method capable of distinguishing between the effects of damage and of the changing environmental conditions affecting damage sensitivity features is proposed. This method eliminates the need to form the baseline of the undamaged structure using damage sensitivity features obtained from a wide range of environmental conditions, as conventionally has been done, and utilizes features from two extreme and opposite environmental conditions as baselines. To allow near real-time monitoring, subsequent measurements are added one at a time to the baseline to create new data sets. Principal component analysis is then introduced for processing each data set so that patterns can be extracted and damage can be distinguished from environmental effects. The proposed method is tested using a two-dimensional truss structure and validated using measurements from the Z24 Bridge which was monitored for nearly a year, with damage scenarios applied to it near the end of the monitoring period. The results demonstrate the robustness of the proposed method for damage detection under changing environmental conditions. The method also works despite the nonlinear effects produced by environmental conditions on damage sensitivity features. Moreover, since each measurement is allowed to be analyzed one at a time, near real-time monitoring is possible. Damage progression can also be given from the method which makes it advantageous for damage evolution monitoring.

scholarly journals Optimizing the structure and movement of a robotic bat with biological kinematic synergies

2018 ◽  
Vol 37 (10) ◽  
pp. 1233-1252 ◽  
Author(s):  
Jonathan Hoff ◽  
Alireza Ramezani ◽  
Soon-Jo Chung ◽  
Seth Hutchinson
Keyword(s):  
Principal Component Analysis ◽  
Topological Structure ◽  
Degrees Of Freedom ◽  
Dimensional Space ◽  
Principal Component ◽  
Biologically Inspired ◽  
Wing Kinematics ◽  
Wing Motion ◽  
Kinematic Synergies ◽  
Low Dimensional

In this article, we present methods to optimize the design and flight characteristics of a biologically inspired bat-like robot. In previous, work we have designed the topological structure for the wing kinematics of this robot; here we present methods to optimize the geometry of this structure, and to compute actuator trajectories such that its wingbeat pattern closely matches biological counterparts. Our approach is motivated by recent studies on biological bat flight that have shown that the salient aspects of wing motion can be accurately represented in a low-dimensional space. Although bats have over 40 degrees of freedom (DoFs), our robot possesses several biologically meaningful morphing specializations. We use principal component analysis (PCA) to characterize the two most dominant modes of biological bat flight kinematics, and we optimize our robot’s parametric kinematics to mimic these. The method yields a robot that is reduced from five degrees of actuation (DoAs) to just three, and that actively folds its wings within a wingbeat period. As a result of mimicking synergies, the robot produces an average net lift improvesment of 89% over the same robot when its wings cannot fold.

scholarly journals Implementation of a Piezo-diagnostics Approach for Damage Detection Based on PCA in a Linux-Based Embedded Platform

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3730 ◽  
Author(s):  
Jhonatan Camacho ◽  
Andrés Quintero ◽  
Magda Ruiz ◽  
Rodolfo Villamizar ◽  
Luis Mujica
Keyword(s):  
Statistical Model ◽  
Damage Detection ◽  
Structural Integrity ◽  
Statistical Processing ◽  
Principal Component ◽  
Detection Methods ◽  
Active System ◽  
Pipe Surface ◽  
Wave Response ◽  
Piezoelectric Devices

The implementation of damage-detection methods for continuously assessing structural integrity entails systems with attractive features such as storage capabilities, memory capacity, computational complexity and time-consuming processing. In this sense, embedded hardware platforms are a promising technology for developing integrated solutions in Structural Health Monitoring. In this paper, design, test, and specifications for a standalone inspection prototype are presented, which take advantage of piezo-diagnostics principle, statistical processing via Principal Component Analysis (PCA) and embedded systems. The equipment corresponds to a piezoelectric active system with the capability to detect defects in structures, by using a PCA-based algorithm embedded in the Odroid-U3 ARM Linux platform. The operation of the equipment consists of applying, at one side of the structure, wide guided waves by means of piezoelectric devices operated in actuation mode and to record the wave response in another side of the structure by using the same kind of piezoelectric devices operated in sensor mode. Based on the nominal response of the guide wave (no damages), represented by means of a PCA statistical model, the system can detect damages between the actuated/sensed points through squared prediction error (Q-statistical index). The system performance was evaluated in a pipe test bench where two kinds of damages were studied: first, a mass is added to the pipe surface, and then leaks are provoked to the pipe structure by means of a drill tool. The experiments were conducted on two lab structures: (i) a meter carbon-steel pipe section and (ii) a pipe loop structure. The wave response was recorded between the instrumented points for two conditions: (i) The pipe in nominal conditions, where several repetitions will be applied to build the nominal statistical model and (ii) when damage is caused to the pipe (mass adding or leak). Damage conditions were graphically recognized through the Q-statistic chart. Thus, the feasibility to implement an automated real-time diagnostic system is demonstrated with minimum processing resources and hardware flexibility.

scholarly journals Small-variance asymptotics for non-parametric online robot learning

2018 ◽  
Vol 38 (1) ◽  
pp. 3-22 ◽  
Author(s):  
Ajay Kumar Tanwani ◽  
Sylvain Calinon
Keyword(s):  
Mixture Models ◽  
Dirichlet Process ◽  
Large Scale ◽  
Principal Component ◽  
Small Variance ◽  
Remote Manipulation ◽  
State Duration ◽  
Duration Information ◽  
Low Dimensional ◽  
Non Parametric

Small-variance asymptotics is emerging as a useful technique for inference in large-scale Bayesian non-parametric mixture models. This paper analyzes the online learning of robot manipulation tasks with Bayesian non-parametric mixture models under small-variance asymptotics. The analysis yields a scalable online sequence clustering (SOSC) algorithm that is non-parametric in the number of clusters and the subspace dimension of each cluster. SOSC groups the new datapoint in low-dimensional subspaces by online inference in a non-parametric mixture of probabilistic principal component analyzers (MPPCA) based on a Dirichlet process, and captures the state transition and state duration information online in a hidden semi-Markov model (HSMM) based on a hierarchical Dirichlet process. A task-parameterized formulation of our approach autonomously adapts the model to changing environmental situations during manipulation. We apply the algorithm in a teleoperation setting to recognize the intention of the operator and remotely adjust the movement of the robot using the learned model. The generative model is used to synthesize both time-independent and time-dependent behaviors by relying on the principles of shared and autonomous control. Experiments with the Baxter robot yield parsimonious clusters that adapt online with new demonstrations and assist the operator in performing remote manipulation tasks.

scholarly journals A Geometric Framework for Understanding Dynamic Information Integration in Context-Dependent Computation

2021 ◽  
Author(s):  
Xiaohan Zhang ◽  
Shenquan Liu ◽  
Zhe Sage Chen
Keyword(s):  
Decision Making ◽  
Prefrontal Cortex ◽  
Information Integration ◽  
Principal Component ◽  
Population Coding ◽  
Geometric Framework ◽  
Context Dependent ◽  
Activity State ◽  
Low Dimensional ◽  
Context Cues

AbstractPrefrontal cortex plays a prominent role in performing flexible cognitive functions and working memory, yet the underlying computational principle remains poorly understood. Here we trained a rate-based recurrent neural network (RNN) to explore how the context rules are encoded, maintained across seconds-long mnemonic delay, and subsequently used in a context-dependent decision-making task. The trained networks emerged key experimentally observed features in the prefrontal cortex (PFC) of rodent and monkey experiments, such as mixed-selectivity, sparse representations, neuronal sequential activity and rotation dynamics. To uncover the high-dimensional neural dynamical system, we further proposed a geometric framework to quantify and visualize population coding and sensory integration in a temporally-defined manner. We employed dynamic epoch-wise principal component analysis (PCA) to define multiple task-specific subspaces and task-related axes, and computed the angles between task-related axes and these subspaces. In low-dimensional neural representations, the trained RNN first encoded the context cues in a cue-specific subspace, and then maintained the cue information with a stable low-activity state persisting during the delay epoch, and further formed line attractors for sensor integration through low-dimensional neural trajectories to guide decision making. We demonstrated via intensive computer simulations that the geometric manifolds encoding the context information were robust to varying degrees of weight perturbation in both space and time. Overall, our analysis framework provides clear geometric interpretations and quantification of information coding, maintenance and integration, yielding new insight into the computational mechanisms of context-dependent computation.

scholarly journals Approximating deformation fields for the analysis of continuous heterogeneity of biological macromolecules by 3D Zernike polynomials

IUCrJ ◽  
2021 ◽  
Vol 8 (6) ◽  
Author(s):  
David Herreros ◽  
Roy R. Lederman ◽  
James Krieger ◽  
Amaya Jiménez-Moreno ◽  
Marta Martínez ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Structural Characteristics ◽  
Normal Mode Analysis ◽  
Principal Component ◽  
Current Data ◽  
Mode Analysis ◽  
Biological Macromolecules ◽  
Mathematical Basis ◽  
Common Framework ◽  
Low Dimensional

Structural biology has evolved greatly due to the advances introduced in fields like electron microscopy. This image-capturing technique, combined with improved algorithms and current data processing software, allows the recovery of different conformational states of a macromolecule, opening new possibilities for the study of its flexibility and dynamic events. However, the ensemble analysis of these different conformations, and in particular their placement into a common variable space in which the differences and similarities can be easily recognized, is not an easy matter. To simplify the analysis of continuous heterogeneity data, this work proposes a new automatic algorithm that relies on a mathematical basis defined over the sphere to estimate the deformation fields describing conformational transitions among different structures. Thanks to the approximation of these deformation fields, it is possible to describe the forces acting on the molecules due to the presence of different motions. It is also possible to represent and compare several structures in a low-dimensional mapping, which summarizes the structural characteristics of different states. All these analyses are integrated into a common framework, providing the user with the ability to combine them seamlessly. In addition, this new approach is a significant step forward compared with principal component analysis and normal mode analysis of cryo-electron microscopy maps, avoiding the need to select components or modes and producing localized analysis.

Sign in / Sign up

Export Citation Format

Share Document