Development Of Neural Networks Research Articles

Model Order Determination: A Multi-Objective Evolutionary Neural Network Scheme

Model Order Determination: A Multi-Objective Evolutionary Neural Network Scheme

Construction of Swimmer's Underwater Posture Training Model Based on Multimodal Neural Network Model.

Swimming monitoring based on acceleration sensor is an emerging research direction in the field of human motion recognition. As a public sport, swimming has a wide audience. The swimming monitoring system can facilitate people to monitor and record their own swimming data, so as to formulate a reasonable training plan. Aiming at the defects of single modal information representation ability, high contingency, and easy to be influenced by the outside world, this paper adopts the underwater posture training model of swimmers to perform multimodal information fusion. In this paper, a multimodal information fusion method based on evolutionary neural network is proposed, and an intelligent perception information processing model of the intelligent subject system is constructed. Aiming at the defect that the accuracy and speed of the underwater posture monitoring of swimmers cannot be guaranteed in a complex environment, an evolutionary neural network optimized by a multimodal adaptive genetic algorithm is constructed to perform multimodal information fusion to ensure the effectiveness of the system in the face of complex information. Regarding attitude detection, it mainly uses the three dimensions of the angle of movement, the influence of gravity, and the strength and speed of the movement to measure. The MPU6050 module processor has a wide range of applications and is a mold processing tool with high performance and level. It completes the data processing, data calculation, and data storage of the inspection system in this paper. This paper further studies the working principle, structure, and operation process of this module and adjusts the time error in the detection of carrier motion and attitude so that the processing function of this module can play an optimal state. Four kinds of swimming posture measurement experiments were carried out on the swimmers, and the experimental data were analyzed. The whole system is controlled by the host computer man-machine interaction software remotely and in real time through commands. The experimental results show that the system realizes the detection of the basic posture, meets the basic requirements of the system design, and provides a certain foundation for the follow-up research.

Real time detection and forecasting technique for asthma disease using speech signal and DENN classifier

Abnormal sound of the lungs associated with asthma and respiratory disease. On the spectrogram, it exhibits continuous sinusoidal qualities across time as well as significant computer properties. In this article, a voice signal and an optimum classifier is used to present a real-time detection and forecasting (RTDF) approach for Asthma illness. For asthma diagnosis and forecasting, the suggested RTDF approach employs the improved whale optimization (IWO) algorithm. RTDF technology is used to classify normal and asthmatic diseases based on changes in voice signals. RTDF technology integrates a variety of working Differential evolutionary neural network (DENN) classifiers that are superior to current SVM classifiers and help prevent the development of asthma suppression. In addition, the digital detection gateway-based secondary output can detect or reject the primary output, making breath detection more reliable for weak respiratory sounds. Implementation is done in conjunction with MATLAB tools and performs performance analysis based on the probability of correct classification. The presentation of the planned process was evaluated using a special signal-to-noise ratio (SNR) using lung sounds from patients and normal subjects.

An Effective Algorithm to Improve Recommender Systems using Evolutionary Computation Algorithms and Neural Network

The growing Internet access and easy access to it have resulted in a significant increase in e-content, which, along with many benefits, has caused problems for users. Internet users simply cannot find the content they need from this massive amount of data. Users are faced with a lot of suggestions for choosing goods, buying items, selecting music and videos, and more. Advantage systems can be used to overcome these problems. Today, with the spread of people’s use of cyberspace, such as web sites and social networks, and increasing the need for conscious and clever selection of people, recommender systems has been extensively investigated. Although the neural network can identify the connections between the inputs and outputs of a dataset, but in order to achieve the proper performance of the neural network, a proper structure should be considered. We will use the mantle algorithm to determine this structure. The mantle algorithm is a form of traditional genetic algorithm that uses local search to reduce the time to achieve optimal response. Genetic algorithms are created to search across the search space, while the local search, the neighborhood of the neighborhood, finds every response found by the genetic algorithm to find better answers. This algorithm seeks to find the optimal values for the parameters of the neural network method, so optimal solutions of the memetic algorithm is considered to be used to set parameters for the neural network method. The results of this study show the desirable performance of the proposed approach in this study.

Data Marketing Optimization Method Combining Deep Neural Network and Evolutionary Algorithm

The design and optimization of personalized marketing strategy have become an important direction for e-commerce enterprises to meet the differentiated needs of consumers, innovate service content, and improve their core competitiveness. It is important to analyze the characteristics of personalized marketing in the e-commerce environment and to study and establish the optimization model of personalized marketing strategy and the model solving method, which are suitable for the application environment. In order to develop a new e-commerce model for consumers, innovate the online service content of enterprises, and improve consumer satisfaction, this paper improved two topological weight evolution methods of evolutionary neural networks and used them as tools for model solving, with the objectives of attracting potential consumers, improving consumer satisfaction, and maximizing revenue. The results of the experiments show that the proposed model is a good one. The experimental results show that the optimization model and model solving method proposed in this paper can efficiently build consumer demand and preference models from large-scale data and can help e-commerce enterprises to formulate accurate personalized promotion and pricing strategies to maximize their profits.

Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics.

Neural networks with a large number of parameters are prone to overfitting problems when trained on a relatively small training set. Introducing weight penalties of regularization is a promising technique for solving this problem. Taking inspiration from the dynamic plasticity of dendritic spines, which plays an important role in the maintenance of memory, this letter proposes a brain-inspired developmental neural network based on dendritic spine dynamics (BDNN-dsd). The dynamic structure changes of dendritic spines include appearing, enlarging, shrinking, and disappearing. Such spine plasticity depends on synaptic activity and can be modulated by experiences-in particular, long-lasting synaptic enhancement/suppression (LTP/LTD), coupled with synapse formation (or enlargement)/elimination (or shrinkage), respectively. Subsequently, spine density characterizes an approximate estimate of the total number of synapses between neurons. Motivated by this, we constrain the weight to a tunable bound that can be adaptively modulated based on synaptic activity. Dynamic weight bound could limit the relatively redundant synapses and facilitate the contributing synapses. Extensive experiments demonstrate the effectiveness of our method on classification tasks of different complexity with the MNIST, Fashion MNIST, and CIFAR-10 data sets. Furthermore, compared to dropout and L2 regularization algorithms, our method can improve the network convergence rate and classification performance even for a compact network.

Robust and Scalable Flat‐Optics on Flexible Substrates via Evolutionary Neural Networks

Flexible Flat-Optics This work, presented in article 2100105 by Andrea Fratalocchi and co-workers, implements an artificial intelligent, end-to-end pipeline for the experimental realization of flexible, broadband ultra-flat optics for vectorial light control. The system takes advantage of “physical” neural networks, engineered into suitably designed optical nanoresonators. The design framework also considers fabrication robustness, furnishing devices that maintain their optical response even under strong stress perturbations and deformations.

Hybrid Multi-Objective Optimization Approach in Water Flooding

AbstractNon-dominated sorting genetic algorithm, second version (NSGA-II) is used as a stochastic optimization technique successfully in different engineering applications. In this study, a data-driven optimization strategy based upon evolutionary neural network (EvoNN) algorithm is developed for providing input into NSGA-II optimization. Evolutionary neural network data-driven model is built and trained using initial solutions generated by NSGA-II optimization coupled with the reservoir simulation model. Evolutionary optimization incorporated in the EvoNN strategy is applied in the trained data-driven model to generate the Pareto optimal solution, which is then used as a guiding input into NSGA-II optimization. The described method is applied in two case studies (i.e., Brugge field model and water injection pattern model). The Pareto optimal solutions obtained with data-driven model guided NSGA-II in both models show improvement in convergence and diversity of the solution. The convergence to the Pareto optimal solution has improved by 9% for case-1 (i.e., Brugge field) and by 43% for case-2 (i.e., water injection pattern model). In addition, the Pareto optimal solution obtained by the proposed hybridization has shown improvement in the water–oil ratio (WOR) up to 6% in the Brugge field and up to 97% in the water injection pattern model. This improvement can lead to wide applications in using evolutionary optimizations in real-field simulation models at acceptable computation time.

A novel asexual-reproduction evolutionary neural network for wind power prediction based on generative adversarial networks

Accurate forecasts of wind power generation are essential for the operation of wind farms. But for the newly developed stations, it is difficult to make accurate prediction because there are no sufficient historical data available. It will thus be interesting to explore new data augmentation and prediction modeling approach adaptive to such new-built wind farms. In this regard, a novel asexual-reproduction evolutionary neural network (ARENN) for short-term wind power prediction based on Wasserstein generative adversarial network with gradient penalty (WGANGP) and ensemble empirical mode decomposition (EEMD) is presented in this paper. To solve the dilemma that new-built wind farms lack sufficient wind power data, the WGANGP is first applied to generate realistic data with a similar distribution of real data to augment the training dataset, which is further decomposed into a series of more stable subsequences by the EEMD so as to reduce the prediction difficulty of the machine learning model. In this study, a novel ARENN prediction model is developed to make the short-term wind power prediction, in which an asexual-reproduction evolutionary approach is first proposed to optimize the neural network based on a set of different loss functions that facilitate the population of network parameters approximating to the global optimum along different error surfaces in the evolutionary process. The proposed approach is validated on the data collected from the wind farm located in Spain and the predicted results demonstrate the advantage of our proposed approach over other methods involved in this study.

Benchmarking Studies Aimed at Clustering and Classification Tasks Using K-Means, Fuzzy C-Means and Evolutionary Neural Networks

Clustering is a widely used unsupervised learning technique across data mining and machine learning applications and finds frequent use in diverse fields ranging from astronomy, medical imaging, search and optimization, geology, geophysics, and sentiment analysis, to name a few. It is therefore important to verify the effectiveness of the clustering algorithm in question and to make reasonably strong arguments for the acceptance of the end results generated by the validity indices that measure the compactness and separability of clusters. This work aims to explore the successes and limitations of two popular clustering mechanisms by comparing their performance over publicly available benchmarking data sets that capture a variety of data point distributions as well as the number of attributes, especially from a computational point of view by incorporating techniques that alleviate some of the issues that plague these algorithms. Sensitivity to initialization conditions and stagnation to local minima are explored. Further, an implementation of a feedforward neural network utilizing a fully connected topology in particle swarm optimization is introduced. This serves to be a guided random search technique for the neural network weight optimization. The algorithms utilized here are studied and compared, from which their applications are explored. The study aims to provide a handy reference for practitioners to both learn about and verify benchmarking results on commonly used real-world data sets from both a supervised and unsupervised point of view before application in more tailored, complex problems.

Robust and Scalable Flat‐Optics on Flexible Substrates via Evolutionary Neural Networks

In the past 20 years, flat‐optics has emerged as a promising light manipulation technology, surpassing bulk optics in performance, versatility, and miniaturization capabilities. As of today, however, this technology is yet to find widespread commercial applications. One of the challenges is obtaining scalable and highly efficient designs that can withstand the fabrication errors associated with nanoscale manufacturing techniques. This problem becomes more severe in flexible structures, in which deformations appear naturally when flat‐optics structures are conformally applied to, for example, biocompatible substrates. Herein, an inverse design platform that enables the fast design of flexible flat‐optics that maintain high performance under deformations of their original geometry is presented. The platform leverages on suitably designed evolutionary large‐scale optimizers, equipped with fast‐trained neural network predictors based on encoder decoder architectures. This approach supports the implementation of flexible flat‐optics robust to both fabrication errors or user‐defined perturbation stress. This method is validated by a series of experiments in which broadband flexible light polarizers, which maintain an average polarization efficiency of 80% over 200 nm bandwidths when measured under large mechanical deformations, are realized. These results could be helpful for the realization of a robust class of flexible flat‐optics for biosensing, imaging, and biomedical devices.

Reservoir Computing for Scalable Hardware with Block‐Based Neural Network

AbstractThis paper presents a reservoir computing technique using Asynchronous Block‐Based Neural Networks (ABBNN). Echo State Networks and Liquid State Machines introduced a new paradigm in artificial neural networks (ANN), known as Reservoir Computing (RC). A recurrent neural network (RNN) in Reservoir Computing is generated randomly, and only a readout is trained. The reservoir computing greatly facilitated the practical RNN application and outperformed classical RNN in many tasks. ABBNN is an extended version of the classical block‐based neural network model. ABBNN, an evolvable neural network model, provides a model‐free estimation of nonlinear dynamical systems. To propose a hardware‐aware model of reservoir computing and high‐speed training, we introduce Block‐Based Reservoir Computing (BBRC). BBRC provides a flexible architecture. The architecture based on the basic blocks provides a regularity that supports scalable hardware. In contrast, BBRC also supports randomness based on the internal configuration. Both are significant features in achieving an optimal hardware reservoir computer. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Evolutionary Neural Network based on Quantum Elephant Herding Algorithm for Modulation Recognition in Impulse Noise

Evolutionary Neural Network based on Quantum Elephant Herding Algorithm for Modulation Recognition in Impulse Noise

Fly visual evolutionary neural network solving large‐scale global optimization

Neurophysiologic achievements claimed that the fly visual system could naturally contribute to a type of artificial computation model which used motion-sensitive neurons to detect the local movement direction changes of moving objects. It, however, still remains open how the neurons' information-processing mechanisms and the inspirations of swarm intelligence can be integrated to serve an interdisciplinary topic between computer vision and intelligence optimization-visual evolutionary neural networks. Hereby, a fly visual evolutionary neural network is developed to solve large-scale global optimization (LSGO), inspired by swarm evolution and the characteristics of fly visual perception. It includes two functional modules, of which one is to generate global and local motion direction activities of visual neural nodes, and the other takes the activities as learning rates to update the nodes' states by a population-like evolutionary strategy. Also, it is used to optimize the structure of a multilayer perceptron to acquire a sample classification model. The theoretical results indicate that the network is convergent and meanwhile the computational complexity mainly depends on the size of the input layer and the dimension of LSGO. The comparative experiments have verified that the network is an extremely competitive optimizer for LSGO problems.

Evolutionary neural network approach simulates large-scale high-entropy alloys

Framework drawing on paired distribution functions and atomic properties propels material generation 1,000 times faster than conventional methods.

Building surrogate models for engineering problems by integrating limited simulation data and monotonic engineering knowledge

The use of surrogate models to replace expensive computations with computer simulations has been widely studied in engineering problems. However, often only limited simulation data is available when designing complex products due to the cost of obtaining this kind of data. This presents a challenge for building surrogate models because the information contained in the limited simulation data is incomplete. Therefore, a method for building surrogate models by integrating limited simulation data and engineering knowledge with evolutionary neural networks (eDaKnow) is presented. In eDaKnow, a neural network uses an evolutionary algorithm to integrate the simulation data and the monotonic engineering knowledge to learn its weights and structure synchronously. This method involves converting both limited simulation data and engineering knowledge into the respective fitness functions. Compared with the previous work of others, we propose a method to train the surrogate model by combining data and knowledge through evolutionary neural network. We take knowledge as fitness function to train the model, and use a network structure self-learning method, which means that there is no need to adjust the network structure manually. The empirical results show that: (1) eDaKnow can be used to integrate limited simulation data and monotonic knowledge into a neural network, (2) the prediction accuracy of the newly constructed surrogate model is increased significantly, and (3) the proposed eDaKnow outperforms other methods on relatively complex benchmark functions and engineering problems.

CONTRIBUTION OF AI TO THE CONSTRUCTION WORLD

Artificial intelligence is a department of computer science and information technological know-how, involved in the research, layout, and application of intelligent computer. Conventional techniques for modeling and optimizing complicated structure systems require big amounts of computing assets, and artificial-intelligence-primarily based solutions can frequently provide treasured alternatives for successfully solving problems inside the civil engineering. This paper summarizes currently evolved methods and theories within the growing path for programs of synthetic intelligence in civil engineering, such as evolutionary computation, neural networks, fuzzy systems, professional machine, reasoning, type, and learning, in addition to others like chaos theory, cuckoo seek, firefly algorithm, know-how-based engineering, and simulated annealing. The primary studies tendencies are also talked about in the end. The paper presents an overview of the advances of synthetic intelligence carried out in civil engineering.

Hysteresis compensation and adaptive control based evolutionary neural networks for piezoelectric actuator

Hysteresis compensation and adaptive control based evolutionary neural networks for piezoelectric actuator

Study on Refined Back-Analysis Method for Stress Field Based on In Situ and Disturbed Stresses

Due to uncertainties in the geological evolution process, engineering geological conditions, and nonuniqueness of the solution for in situ stress regression analysis, stress field regression has always been a difficult issue in geotechnical engineering. In view of this problem, a refined back-analysis method for the stress field is proposed in this study based on in situ stress and disturbed stress. First, the in situ stress and disturbed stress in the unloading zone are measured by field tests. The process of geological evolution and excavation disturbance is numerically simulated. The theoretical values of in situ stress and disturbed stress are obtained. The nonlinear mapping relationship of the boundary condition and the stresses at the measuring points is established by the evolutionary neural network. The measured in situ stress and disturbed stress in the unloading zone are imported into the neural network to obtain the boundary conditions. Finally, the boundary condition obtained by back analysis is assigned to the numerical model for calculating the stress field at the project site. The method proposed in this study was applied to analyze the stress field of Mengku Iron Mine in Xinjiang, China. It was found that the accuracy of back-analysis results has been greatly improved because the contributions of both the in situ stress and the disturbed stress were considered in the proposed method. Meanwhile, according to the engineering analysis, the maximum horizontal principal stress in the open-pit slope was reduced by a certain degree, with a maximum reduction of 30%–40% after mining. However, the major principal stress at 0–350 m below the mine pit increased remarkably, with an increment of above 60% compared to the in situ stress. It indicated that excavation unloading has a great influence on the local stress field.

A Quantum Approach Towards the Adaptive Prediction of Cloud Workloads

This work presents a novel Evolutionary Quantum Neural Network (EQNN) based workload prediction model for Cloud datacenter. It exploits the computational efficiency of quantum computing by encoding workload information into qubits and propagating this information through the network to estimate the workload or resource demands with enhanced accuracy proactively. The rotation and reverse rotation effects of the Controlled-NOT (C-NOT) gate serve activation function at the hidden and output layers to adjust the qubit weights. In addition, a Self Balanced Adaptive Differential Evolution (SB-ADE) algorithm is developed to optimize qubit network weights. The accuracy of the EQNN prediction model is extensively evaluated and compared with seven state-of-the-art methods using eight real world benchmark datasets of three different categories. Experimental results reveal that the use of the quantum approach to evolutionary neural network substantially improves the prediction accuracy up to 91.6% over the existing approaches.