Multidimensional cerebellar computations for flexible kinematic control of movements

Both the environment and our body keep changing dynamically. Hence, ensuring movement precision requires adaptation to multiple demands occurring simultaneously. Here we show that the cerebellum performs the necessary multi-dimensional computations for the flexible control of different movement parameters depending on the prevailing context. This conclusion is based on the identification of a manifold-like activity in both mossy fibers (MF, network input) and Purkinje cells (PC, output), recorded from monkeys performing a saccade task. Unlike MFs, the properties of PC manifolds developed selective representations of individual movement parameters. Error feedback-driven climbing fiber input modulated the PC manifolds to predict specific, error type-dependent changes in subsequent actions. Furthermore, a feed-forward network model that simulated MF-to-PC transformations revealed that amplification and restructuring of the lesser variability in the MF activity is a pivotal circuit mechanism. Therefore, flexible control of movement by the cerebellum crucially depends on its capacity for multi-dimensional computations.

Predicting Shear Strength in FRP-Reinforced Concrete Beams Using Bat Algorithm-Based Artificial Neural Network

In this article, 140 samples with different characteristics were collected from the literature. The Feed Forward network is used in this research. The parameters f’c (MPa), ρf (%), Ef (GPa), a/d, bw (mm), d (mm), and VMA are selected as inputs to determine the shear strength in FRP-reinforced concrete beams. The structure of the artificial neural network (ANN) is also optimized using the bat algorithm. ANN is also compared to the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithm. Finally, Nehdi et al.’s model, ACI-440, and BISE-99 equations were used to evaluate the models’ accuracy. The results confirm that the bat algorithm-optimized ANN is more capable, flexible, and provides superior precision than the other three models in determining the shear strength of the FRP-reinforced concrete beams.

Preference Net: Image Recognition using Ranking Reduction to Classification

Accuracy and computational cost are the main challenges of deep neural networks in image recognition. This paper proposes an efficient ranking reduction to binary classification approach using a new feed-forward network and feature selection based on ranking the image pixels. Preference net (PN) is a novel deep ranking learning approach based on Preference Neural Network (PNN), which uses new ranking objective function and positive smooth staircase (PSS) activation function to accelerate the image pixels’ ranking. PN has a new type of weighted kernel based on spearman ranking correlation instead of convolution to build the features matrix. The PN employs multiple kernels that have different sizes to partial rank image pixels’ in order to find the best features sequence. PN consists of multiple PNNs’ have shared output layer. Each ranker kernel has a separate PNN. The output results are converted to classification accuracy using the score function. PN has promising results comparing to the latest deep learning (DL) networks using the weighted average ensemble of each PN models for each kernel on CFAR-10 and Mnist-Fashion datasets in terms of accuracy and less computational cost.

A novel out of step relaying algorithm based on wavelet transform and a deep learning machine model

Out-of-step protection of one or a group of synchronous generators is unreliable in a power system which has significant renewable power penetration. In this work, an innovative out-of-step protection algorithm using wavelet transform and deep learning is presented to protect synchronous generators and transmission lines. The specific patterns are generated from both stable and unstable power swing, and three-phase fault using the wavelet transform technique. Data containing 27,008 continuous samples of 48 different features is used to train a two-layer feed-forward network. The proposed algorithm gives an automatic, setting free and highly accurate classification for the three-phase fault, stable power swing, and unstable power swing through pattern recognition within a half cycle. The proposed algorithm uses the Kundur 2-area system and a 29-bus electric network for testing under different swing center locations and levels of renewable power penetration. Hardware-in-the-loop (HIL) tests show the hardware compatibility of the developed out-of-step algorithm. The proposed algorithm is also compared with recently reported algorithms. The comparison and test results on different large-scale systems show that the proposed algorithm is simple, fast, accurate, and HIL tested, and not affected by changes in power system parameters.

Multi-path Convolutional Neural Network to identify Tumorous Sub-classes for Breast Tissue from Histopathological Images

Malignancy is one of the leading causes of death globally. It is on the rise in the developed and low-income countries with survival rates of less than 40%. However, early diagnosis may increase survival chances. Histopathology images acquired from the biopsy are a popular method for cancer diagnosis. In this article, we propose a deep convolutional neural network-based method that helps classify breast cancer tumor subtypes from histopathology images. The model is trained on the BreakHis dataset but is also tested on images from other datasets. The model is trained to recognized eight different tumor subtypes, and also to perform binary classification (malignant / non-malignant). The CNN model uses an encoder-decoder architecture as well as a parallel feed-forward network. The proposed model provides higher cumulative training accuracy and statistical scoring after five-fold cross-validation. Comparing with the other models, the accuracy of the proposed model is higher at different magnification and patient levels.

Near-Optimal Sparse Neural Trees for Supervised Learning

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980s. On the other hand, deep learning methods have boosted the capacity of machine learning algorithms and are now being used for non-trivial applications in various applied domains. But training a fully-connected deep feed-forward network by gradient-descent backpropagation is slow and requires arbitrary choices regarding the number of hidden units and layers. In this paper, we propose near-optimal neural regression trees, intending to make it much faster than deep feed-forward networks and for which it is not essential to specify the number of hidden units in the hidden layers of the neural network in advance. The key idea is to construct a decision tree and then simulate the decision tree with a neural network. This work aims to build a mathematical formulation of neural trees and gain the complementary benefits of both sparse optimal decision trees and neural trees. We propose near-optimal sparse neural trees (NSNT) that is shown to be asymptotically consistent and robust in nature. Additionally, the proposed NSNT model obtain a fast rate of convergence which is near-optimal up to some logarithmic factor. We comprehensively benchmark the proposed method on a sample of 80 datasets (40 classification datasets and 40 regression datasets) from the UCI machine learning repository. We establish that the proposed method is likely to outperform the current state-of-the-art methods (random forest, XGBoost, optimal classification tree, and near-optimal nonlinear trees) for the majority of the datasets.

Firefly Algorithm Optimized Functional Link Artificial Neural Network for ISA-Radar Image Recognition

Traditional neural networks are very diverse and have been used during the last decades in the fields of data classification. These networks like MLP, back propagation neural networks (BPNN) and feed forward network have shown inability to scale with problem size and with the slow convergence rate. So in order to overcome these numbers of drawbacks, the use of higher order neural networks (HONNs) becomes the solution by adding input units along with a stronger functioning of other neural units in the network and transforms easily these input units to hidden layers. In this paper, a new metaheuristic method, Firefly (FFA), is applied to calculate the optimal weights of the Functional Link Artificial Neural Network (FLANN) by using the flashing behavior of fireflies in order to classify ISA-Radar target. The average classification result of FLANN-FFA which reached 96% shows the efficiency of the process compared to other tested methods.

Spatial-Prior-Guided Attention for Small Object Detection in Overhead Catenary System

The small defects in overhead catenary system (OCS) can result in long time delays, economic loss and even passenger injury. However, OCS images exhibit great variations with complex background and oblique views which pose a great challenge for small defects detection in high-speed rail system. In this paper, we propose the spatial-prior-guided attention for small object detection in OCS with two main advantages: (1) The spatial-prior is proposed to retain the spatial information between small defects and the electric components in OCS. (2) Based on spatial-prior, the spatial-prior-guided attention model (SAM) is designed to highlight useful information in the features and suppress redundant features response. SAM can model the spatial relations progressively and can be integrated with state-of-the-art feed-forward network architecture with end-to-end training fashion. We conduct extensive experiments on both Split pin datasets and PASCAL–VOC datasets and achieve 97.2% and 79.5% mAP values, respectively. All the experiments demonstrate the competitive performance of our method.

Experimental Analysis And Parameter Optimization On The Reduction of NOx From Diesel Engine Using RSM And ANN Model

The feasibility of the Non-thermal Plasma (NTP) process is examined by four operating parameters including NOx concentration (300-400 ppm), gas flow rate (2-6 lpm), voltage (20-30 kV) and electrode gap (3-5 mm) using a Dielectric Barrier Discharge (DBD) reactor for removing NOx from diesel engine exhaust. Based on the NTP study, the NOx removal efficiency and energy efficiency of the NTP reactor are measured. Optimization of process parameters have been carried out using response surface-based Box Behnken Design (BBD) method and Artificial Neural Network (ANN) method. ANN based optimization is carried out using feed-forward network algorithm which has 4 input nodes, 10 hidden nodes and 2 output nodes. Based on the RSM and ANN model study, R2 value are obtained as 0.98 and 0.99 respectively. These models demonstrates that they have strong agreement with the experimental results. The results are indicated that the RSM model's optimum conditions resulted in a maximum NOx reduction of 60.5% and an energy efficiency of 66.24 g/J. The comparison between the two models confirmed the findings, whereas this ANN model displayed a stronger correlation to the experimental evidence.