Ants Colony Optimization Algorithm in the Hopfield Neural Network for Agricultural Soil Fertility Reverse Analysis

The Boolean Satisfiability Problem (BSAT) is one of the most important decision problems in mathematical logic and computational sciences for determining whether or not a solution to a Boolean formula.. Hopfield neural network (HNN) is one of the major type artificial neural network (NN) popularly known for it used in solving various optimization and decision problems based on its energy minimization machinism. The existing models that incorporate standalone network projected non-versatile framework as fundamental Hopfield type of neural network (HNN) employs random search in its training stages and sometimes get trapped at local optimal solution. In this study, Ants Colony Optimzation Algorithm (ACO) as a novel variant of probabilistic metaheuristic algorithm (MA) inspired by the behavior of real Ants, has been incorporated in the training phase of Hopfield types of the neural network (HNN) to accelerate the training process for Random Boolean kSatisfiability reverse analysis (RANkSATRA) based for logic mining. The proposed hybrid model has been evaluated according to robustness and accuracy of the induced logic obtained based on the agricultural soil fertility data set (ASFDS). Based on the experimental simulation results, it reveals that the ACO can effectively work with the Hopfield type of neural network (HNN) for Random 3 Satisfiability Reverse Analysis with 87.5 % classification accuracy

IMU Sensing–Based Hopfield Neuromorphic Computing for Human Activity Recognition

Aiming at the self-association feature of the Hopfield neural network, we can reduce the need for extensive sensor training samples during human behavior recognition. For a training algorithm to obtain a general activity feature template with only one time data preprocessing, this work proposes a data preprocessing framework that is suitable for neuromorphic computing. Based on the preprocessing method of the construction matrix and feature extraction, we achieved simplification and improvement in the classification of output of the Hopfield neuromorphic algorithm. We assigned different samples to neurons by constructing a feature matrix, which changed the weights of different categories to classify sensor data. Meanwhile, the preprocessing realizes the sensor data fusion process, which helps improve the classification accuracy and avoids falling into the local optimal value caused by single sensor data. Experimental results show that the framework has high classification accuracy with necessary robustness. Using the proposed method, the classification and recognition accuracy of the Hopfield neuromorphic algorithm on the three classes of human activities is 96.3%. Compared with traditional machine learning algorithms, the proposed framework only requires learning samples once to get the feature matrix for human activities, complementing the limited sample databases while improving the classification accuracy.

Halanay inequality involving Caputo-Hadamard fractional derivative and application

A Halanay inequality with distributed delay of non-convolution type is considered. We establish a decay of solutions as a Mittag-Leffler function composed with a logarithmic function. A general sufficient condition is found and a large class of admissible retardation kernels is provided. This needs the preparation of several lemmas on properties of the Hadamard derivative and some basic fractional differential problems with this kind of derivative. The obtained result is then applied to a Hopfield neural network system to discuss its stability.

Neural Network Algorithm for Stabilizing Mechanized Systems

The article describes an experimental model of stabilization of a mechanized system. The following are shown: a skate; an element of the program code; an algorithm for stabilizing a proportional-integral-differential controller (PID). The experimental model uses the calculation and adjustment of the regulator according to the Ziegler-Nichols method. For the case of applying the neural network approach to the search for equilibrium, the Hopfield neural network is used. The technology of calculating the balancing of the values of the coefficients: proportional, integral, differential components are described. The design of the rolling system is described. The experimental model is designed to identify the balancing range of the rolling system of small-diameter balls. The experimental module balances the ball at a distance of 4.5 to 7 cm (SW-range). The shortcomings of the experimental model of stabilization of the mechanized system are revealed. The analysis of experimental studies of spacecraft stabilization is carried out. It is determined that it is advisable to use the mathematical tools of the sixth-order Butterworth polynomial in the training of a neural network. Complex neural network calculations make it possible to calculate the stabilization coefficients of the spacecraft when the coordinate system does not coincide with the axes of inertia. An overview of the authors ' research on the use of intelligent quality control systems for the production of medicines is given. An overview of neural network solutions for stabilizing the turning angle of high-speed cars is given. The expediency of selecting the stabilization coefficients of a proportional-integral-differential regulator by a trained neural network for various rolling ranges is proved.

Optimal CNN–Hopfield Network for Pattern Recognition Based on a Genetic Algorithm

Convolutional neural networks (CNNs) have powerful representation learning capabilities by automatically learning and extracting features directly from inputs. In classification applications, CNN models are typically composed of: convolutional layers, pooling layers, and fully connected (FC) layer(s). In a chain-based deep neural network, the FC layers contain most of the parameters of the network, which affects memory occupancy and computational complexity. For many real-world problems, speeding up inference time is an important matter because of the hardware design implications. To deal with this problem, we propose the replacement of the FC layers with a Hopfield neural network (HNN). The proposed architecture combines both a CNN and an HNN: A pretrained CNN model is used for feature extraction, followed by an HNN, which is considered as an associative memory that saves all features created by the CNN. Then, to deal with the limitation of the storage capacity of the HNN, the proposed work uses multiple HNNs. To optimize this step, the knapsack problem formulation is proposed, and a genetic algorithm (GA) is used solve it. According to the results obtained on the Noisy MNIST Dataset, our work outperformed the state-of-the-art algorithms.

Fish Swarm Optimized Deep Hopfield Neural Network-Assisted HCI System for Augmentative Communication Using a Visual Feedback System

In this context, the uses of computers, the Human-computer interface (HCI) system, can assist interaction on-demand services. HCI method facilitates ventilated patients to interact with computers about their needs using their brain’s electrical activity. To accomplish this, an HCI framework is developed in this research to facilitate visual feedback system (VFS) using an augmentative communication approach. Augmentative communication (AC.) or icon-based services are incorporated with a portable monitor placed in front of a patient; they can look at the screen to select (ask) their appropriate needs-related icons. The services have been achieved by capturing and processing patients’ electromagnetic brain activates during the icon selection by their eye flickering moment recording using wearable Electroencephalogram (EEG). The flickering icons on the screen conveying an appropriate message to the monitoring unit computer, and the monitoring unit can respond to the patient’s request using VFS. The HCI system is comprised of the following methodologies to achieve augmentative communication-based services such as EEG signals acquisition, filtering, partition-based feature extraction, and fusion and fish swarm optimized Deep Hopfield neural network FSODHNN based classifier. The evolution results of the VSF based HCI framework are demonstrated successfully. It obtained the highest accuracy of 99.11%, specificity of 99.05%, the sensitivity of 99.09%, and the lowest RMSE of 0.98, MSE of 0.92 in icon identification/selection.

Multistable Dynamics in a Hopfield Neural Network Under Electromagnetic Radiation and Dual Bias Currents

This paper investigates a Hopfield neural network (HNN) under the simulation of external electromagnetic radiation and dual bias currents, in which the fluctuation of magnetic flux across the neuron membrane is used to emulate the influence of electromagnetic radiation. Utilizing conventional analytical methods, the basic properties of the proposed Hopfield neural network are discussed. Due to the addition of electromagnetic radiation and dual bias currents, the Hopfield neural network shows high sensitivity to system parameters and initial conditions. The proposed Hopfield neural network possesses multistability with periodic attractor, quasi-periodic attractor, chaotic attractor and transient chaotic attractor, and all of the attractors are hidden attractors because there is no equilibrium point in the system. In particular, when the neuron membrane magnetic flux is different, the system can present transient chaos with different chaotic times. More interestingly, with the change of system parameters, the proposed Hopfield neural network can exhibit parallel bifurcation behaviors. Finally, the Multisim simulation and hardware experiment results based on discrete electronic components are conducted to support the numerical ones. These results could give useful information to the study of nonlinear dynamic characteristics of the Hopfield neural network.