ARRAY RADIATION PATTERN RECOVERY UNDER RANDOM ERRORS USING CLUSTERED LINEAR ARRAY

In practice, random errors in the excitations (amplitude and phase) of array elements cause undesired variations in the array patterns. In this paper, the clustered array elements with tapered amplitude excitations technique are introduced to reduce the impact of random weight errors and recover the desired patterns. The most beneficial feature of the suggested method is that it can be used in the design stage to count for any amplitude errors instantly. The cost function of the optimizer used is restricted to avoid any unwanted rises in sidelobe levels caused by unexpected perturbation errors. Furthermore, errors on element amplitude excitations are assumed to occur either randomly or sectionally (i.e., an error affecting only a subset of the array elements) through the entire array aperture. The validity of the proposed approach is entirely supported by simulation studies.

Accelerating multi-objective neural architecture search by random-weight evaluation

For the goal of automated design of high-performance deep convolutional neural networks (CNNs), neural architecture search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments. To address this issue, we first introduce a new performance estimation metric, named random-weight evaluation (RWE) to quantify the quality of CNNs in a cost-efficient manner. Instead of fully training the entire CNN, the RWE only trains its last layer and leaves the remainders with randomly initialized weights, which results in a single network evaluation in seconds. Second, a complexity metric is adopted for multi-objective NAS to balance the model size and performance. Overall, our proposed method obtains a set of efficient models with state-of-the-art performance in two real-world search spaces. Then the results obtained on the CIFAR-10 dataset are transferred to the ImageNet dataset to validate the practicality of the proposed algorithm. Moreover, ablation studies on NAS-Bench-301 datasets reveal the effectiveness of the proposed RWE in estimating the performance compared to existing methods.

Region Matching of SAR Images Using Blocks for Target Recognition

A synthetic aperture radar (SAR) target recognition method based on image blocking and matching is proposed. The test SAR image is first separated into four blocks, which are analyzed and matched separately. For each block, the monogenic signal is employed to describe its time-frequency distribution and local details with a feature vector. The sparse representation-based classification (SRC) is used to classify the four monogenic feature vectors and produce the reconstruction error vectors. Afterwards, a random weight matrix with a rich set of weight vectors is used to linearly fuse the feature vectors and all the results are analyzed in a statistical way. Finally, a decision value is designed based on the statistical analysis to determine the target label. The proposed method is tested on the moving and stationary target acquisition and recognition (MSTAR) dataset and the results confirm the validity of the proposed method.

An Efficient Classification Model using Fuzzy Rough Set Theory and Random Weight Neural Network

In the area of fuzzy rough set theory (FRST), researchers have gained much interest in handling the high-dimensional data. Rough set theory (RST) is one of the important tools used to pre-process the data and helps to obtain a better predictive model, but in RST, the process of discretization may loss useful information. Therefore, fuzzy rough set theory contributes well with the real-valued data. In this paper, an efficient technique is presented based on Fuzzy rough set theory (FRST) to pre-process the large-scale data sets to increase the efficacy of the predictive model. Therefore, a fuzzy rough set-based feature selection (FRSFS) technique is associated with a Random weight neural network (RWNN) classifier to obtain the better generalization ability. Results on different dataset show that the proposed technique performs well and provides better speed and accuracy when compared by associating FRSFS with other machine learning classifiers (i.e., KNN, Naive Bayes, SVM, decision tree and backpropagation neural network).

Deep ConvNet: Non-Random Weight Initialization for Repeatable Determinism, Examined with FSGM

A repeatable and deterministic non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM). Using the FSGM approach as a technique to measure the initialization effect with controlled distortions in transferred learning, varying the dataset numerical similarity. The focus is on convolutional layers with induced earlier learning through the use of striped forms for image classification. Which provided a higher performing accuracy in the first epoch, with improvements of between 3–5% in a well known benchmark model, and also ~10% in a color image dataset (MTARSI2), using a dissimilar model architecture. The proposed method is robust to limit optimization approaches like Glorot/Xavier and He initialization. Arguably the approach is within a new category of weight initialization methods, as a number sequence substitution of random numbers, without a tether to the dataset. When examined under the FGSM approach with transferred learning, the proposed method when used with higher distortions (numerically dissimilar datasets), is less compromised against the original cross-validation dataset, at ~31% accuracy instead of ~9%. This is an indication of higher retention of the original fitting in transferred learning.

Deep ConvNet: Non-Random Weight Initialization for Repeatable Determinism, examined with FSGM

This paper presents a non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM) attack. This paper's focus is convolutional layers, and are the layers that have been responsible for better than human performance in image categorization. The proposed method induces earlier learning through the use of striped forms, and as such has less unlearning of the existing random number speckled methods, consistent with the intuitions of Hubel and Wiesel. The proposed method provides a higher performing accuracy in a single epoch, with improvements of between 3-5% in a well known benchmark model, of which the first epoch is the most relevant as it is the epoch after initialization. The proposed method is also repeatable and deterministic, as a desirable quality for safety critical applications in image classification within sensors. That method is robust to Glorot/Xavier and He initialization limits as well. The proposed non-random initialization was examined under adversarial perturbation attack through the FGSM approach with transferred learning, as a technique to measure the affect in transferred learning with controlled distortions, and finds that the proposed method is less compromised to the original validation dataset, with higher distorted datasets.

Invertibility of Generalized Space-Time Autoregressive Model with Random Weight

The generalized linear process accomplishes stationarity and invertibility properties. The invertibility property must be having a series of convergence conditions of the process parameter. The generalized Space-Time Autoregressive (GSTAR) model is one of the stationary linear models therefore it is necessary to reveal the invertibility through the convergence of the parameter series. This article studies the invertibility of model GSTAR(1;1) with kernel random weight. The result shows that the model GSTAR(1;1) under kernel random weight fulfills the invertibility property and obtains a finite order of Generalized Space-Time Moving Average (GSTMA) process. The other result obtained is the time order of the finite orde . On the Triangular kernel resulted in the relatively great value n, so that it does not apply to the kernel with a finite value n.

Scale-free percolation in continuous space: quenched degree and clustering coefficient

Spatial random graphs capture several important properties of real-world networks. We prove quenched results for the continuous-space version of scale-free percolation introduced in [14]. This is an undirected inhomogeneous random graph whose vertices are given by a Poisson point process in $\mathbb{R}^d$. Each vertex is equipped with a random weight, and the probability that two vertices are connected by an edge depends on their weights and on their distance. Under suitable conditions on the parameters of the model, we show that, for almost all realizations of the point process, the degree distributions of all the nodes of the graph follow a power law with the same tail at infinity. We also show that the averaged clustering coefficient of the graph is self-averaging. In particular, it is almost surely equal to the annealed clustering coefficient of one point, which is a strictly positive quantity.

Research on vehicle stability region under critical driving situations with static bifurcation theory

A strategy for solving the static bifurcation points of the 5DOF vehicle nonlinear system is proposed to research the stability region of the system. The bifurcation characteristics of the system is changed by the coupling of the steering and the engine braking torques under the high-speed emergency steering conditions, and the corresponding vehicle stability region must be redefined. The stability region of the vehicle which is influenced by the engine braking torque is determined with the static bifurcation theory, and the equilibrium points of the 5DOF vehicle system are solved with the phase space method and the random weight particle swarm optimization (RWPSO) algorithm. The vehicle stability is verified with different initial longitudinal speeds and different steering angles, and the simulation results validate the effectiveness of the stability region under the critical driving conditions. The study is conducive to the development of the active safety control systems and the application of nonlinear system dynamics in the automotive field. Furthermore, it provides the theoretical support for the application of the vehicle-handling stability.