Search

This paper presents an in-depth study and analysis of oil painting classification and simulation using an improved embedded learning fusion vision perception algorithm. This paper analyzes and models the image quality evaluation problem by simulating the human visual system and extracting quality perception features as the main entry point to improve the prediction accuracy of the overall algorithm. This paper proposes a multi-classification method of CCNN, which uses the similarity measure based on information first to achieve multi-classification of artwork styles and artists, and this part is the main part of this paper. This paper uses the wiki art repository to construct a dataset of oil paintings, including over 2000 works by 20 artists in 13 styles. CNN achieves an accuracy of 85.75% on the artist classification task, which is far more effective than traditional deep learning networks such as Resnet. Finally, we use the network model of this paper and other network models to train the classification of 3, 4, and 6 categories of art images. The accuracy of art image classification by this paper's algorithm is higher than that of the current mainstream convolutional neural network models, and the extracted features are more comprehensive and more accurate than traditional art image feature extraction methods, which do not rely on researchers to extract image features. Experiments show that the proposed method can achieve excellent prediction accuracy for both synthetic distorted images and distorted images. [ABSTRACT FROM AUTHOR]

Mathematical modeling of many natural and physical phenomena in industry, engineering sciences and basic sciences lead to linear and non-linear devices. In many cases, the coefficients of these devices, taking into account qualitative or linguistic concepts, show their complexity in the form of Z-numbers. Since Z-number involves both fuzziness and reliability or probabilistic uncertainty, it is difficult to obtain the exact solution to the problems with Z-number. In this work, a method and an algorithm are proposed for the approximate solution of a Z-number linear system of equations as an important case of such problems. The paper is devoted to solving linear systems where the coefficients of the variables and right hand side values are Z-numbers. An algorithm is presented based on a ranking scheme and the neural network technique to solve the obtained system. Moreover, two examples are included to describe the procedure of the method and results. [ABSTRACT FROM AUTHOR]

The global economy appears the trend of anti-globalization under the influence of COVID-19. Based on the input-output table of lead database from 2006 to 2020, this paper divides the factors that affect the development of financial industry in China, the United States and Russia into six aspects: price, intermediate input, household consumption, government consumption, export and import. ADGA-BP neural network model is proposed in this paper, which is based on six aspects of price, intermediate input, consumer, government consumption, export and import. The intermediate input is decomposed from the perspective of industrial structure to study the interrelationship between financial industry and other industries in the three countries. The results show that the intermediate input is the main factor in the development of financial industry in the three countries, but the source industries of the intermediate input are not the same; the two factors of household consumption and price are closely related to the development of financial industry in the three countries, and they all play a role in promoting China, while the relationship between household consumption and the United States and between price and Russia is reverse; Government consumption only has a significant impact on Russia; from the perspective of mutual influence, the mutual investment between the financial industry of China and the United States is relatively large, while the relationship between the Russian financial industry and the two countries is relatively weak. It shows that under the background of covid-19, the development of financial industry is affected. [ABSTRACT FROM AUTHOR]

As the stability of surrounding rock of coal roadway is affected by many factors, which makes the classification result hard to be consistent with the field practice. To solve the above problems, this paper proposes a method for the classification of stability of rock which is present in roadway of coal using the artificial intelligence algorithm. In this paper, the influencing factors of stability of rock which is present in roadway are analyzed, and seven influential factors are selected as classification indexes. To solve the problem of slow convergence speed and easy to fall into the local minimum of the back propagation artificial neural network (BP-ANN), an improved BP-ANN algorithm based on additional momentum and Levenberg-Marquardt optimization is proposed based on the analysis of the existing improved methods, which improves the convergence speed and avoids the local minimum effectively. Based on the learning model available, classification system based on fuzzy rule have been implemented and yielded better behavior in the situation of uncertain data sets. Finally, the stability classification model of surrounding rocks of coal roadway using BP-ANN was established in MATLAB environment, and the model was applied to 13 data samples of coal roadway for testing, with the identification rate of 92.3%. The experimental results verify that the method proposed based on fuzzy rule classification system in this paper has a high accuracy of type identification and is applicable to the stability classification of surrounding rock in the coal roadway. [ABSTRACT FROM AUTHOR]

Intelligent video analysis has broad application prospects. How to automatically analyze and identify human behavior in video has attracted extensive attention from researchers at home and abroad. Moreover, researching effective video behavior recognition algorithms and designing efficient behavior recognition systems has important theoretical and practical value. This paper studies the nonlinear classification technique and applies the video behavior recognition algorithm to basketball recognition. Moreover, this paper studies the classical convolutional neural network model and several improvements. In addition, this paper explains the advantages of convolutional neural networks in feature extraction compared with traditional neural networks and analyzes the performance of the algorithm by designing actual experiments. The research results show that the algorithm can quickly identify multiple players on the field, and the method can effectively deal with occlusion and other issues with high accuracy and real-time. [ABSTRACT FROM AUTHOR]

A convolutional neural network combined with attention mechanism and a parallel joint algorithm model (CATTB) of bidirectional independent recurrent neural network are proposed. The algorithm extracts the relocation feature and the "texture fingerprint" feature for expressing the similarity of the URL (Uniform Resource Locator) binary file content of the malicious web page, and uses the word vector tool word2vec to train the URL word vector feature and extract the URL static vocabulary feature. CNN (Convolutional Neural Network) is used to extract deep local features. Secondly, Attention mechanism adjusts weight and BiIndRNN (Bidirectional Independently Recurrent Neural Network) to extract global features. Finally, softmax is used for classification. This paper extracts more comprehensive features from different angles and using different methods. The experimental results show that the test results are higher than other researchers, and compared with other algorithms, the proposed CATTB algorithm improves the accuracy of malicious web page detection. [ABSTRACT FROM AUTHOR]

Fuzzy English recognition is affected by many factors, which leads to certain accuracy problems in intelligent recognition results. In order to improve the automatic recognition efficiency of fuzzy English, based on machine learning technology, this study constructs a neural network model. At the same time, this paper analyzes the research status and existing problems of handwritten character recognition, analyzes the model, and adopts multiple modules for automatic English recognition. In addition, the system is built on the basis of algorithms and model support, which makes fuzzy English recognition intelligent. Finally, in order to study the algorithm and model performance, the fuzzy English recognition is carried out through experiments. The research shows that the model constructed in this paper has certain recognition effect, which can be applied to practice, and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

Due to the strict personnel control measures in COVID-19 epidemic, the control system cannot be maintained and managed manually. This puts forward higher requirements for the accuracy of its fault-tolerant performance. The control system plays an increasingly important role in the rapid development of industrial production. When the sensor in the system fails, the system will become unstable. Therefore, it is necessary to accurately and quickly diagnose the faults of the system sensors and maintain the system in time. This paper takes the control system as the object to carry out the fault diagnosis and fault-tolerant control research of its sensors. A network model of wavelet neural network is proposed, and an improved genetic algorithm is used to optimize the weights and thresholds of the neural network model to avoid the deficiencies of traditional neural network algorithms. For the depth sensor of a certain system, an online fault diagnosis scheme based on RBF (Radial Basis Function) neural network and genetic algorithm optimized neural network was designed. The disturbance fault, "stuck" fault, drift fault and oscillation fault of the depth sensor are simulated. Simulation experiments show that both online fault diagnosis schemes can accurately identify sensor faults and the genetic algorithm optimized neural network is superior to RBF neural network in both recognition accuracy and training time under the influence of COVID-19. [ABSTRACT FROM AUTHOR]

Under the influence of COVID-19, an efficient Ad-hoc network routing algorithm is required in the process of epidemic prevention and control. Artificial neural network has become an effective method to solve large-scale optimization problems. It has been proved that the appropriate neural network can get the exact solution of the problem in real time. Based on the continuous Hopfield neural network (CHNN), this paper focuses on the study of the best algorithm path for QoS routing in Ad-hoc networks. In this paper, a new Hopfield neural network model is proposed to solve the minimum cost problem in Ad-hoc networks with time delay. In the improved version of the path algorithm, the relationship between the parameters of the energy function is provided, and it is proved that the feasible solution of the network belongs to the category of progressive stability by properly selecting the parameters. The calculation example shows that the solution is not affected by the initial value, and the global optimal solution can always be obtained. The algorithm is very effective in the prevention and control in COVID-19 epidemic. [ABSTRACT FROM AUTHOR]

Curriculum is the basis of vocational training, its development level and teaching efficiency determine the realization of vocational training objectives, as well as the quality and level of major vocational academic training. Therefore, the development of curriculum is an important issue. And affect the school's teaching capacity building. The analysis of the latest developments in the main courses shows that there are some deviations or irrationalities in the curriculum in some colleges and universities, and the general problems of understanding the latest courses, such as lack of solid foundation in curriculum setting, unclear direction of objectives, unclear reform ideas, inadequate and systematic construction measures, lack of attention to the quality of education. This paper explains the rules for the establishment of first-level courses, clarifies the ideas and priorities of architecture, and explores strategies for building university-level courses using knowledge of artificial intelligence and neural network algorithms in order to gain experience from them. [ABSTRACT FROM AUTHOR]

In this paper, a speech-to-text translation model has been developed for Malaysian speakers based on 41 classes of Phonemes. A simple data acquisition algorithm has been used to develop a MATLAB graphical user interface (GUI) for recording the isolated word speech signals from 35 non-native Malaysian speakers. The collected database consists of 86 words with 41 classes of phoneme based on Affricatives, Diphthongs, Fricatives, Liquid, Nasals, Semivowels and Glides, Stop and Vowels. The speech samples are preprocessed to eliminate the undesirable artifacts and the fuzzy voice classifier has been employed to classify the samples into voiced sequence and unvoiced sequence. The voiced sequences are divided into frame segments and for each frame, the Linear Predictive co-efficients features are obtained from the voiced sequence. Then the feature sets are formed by deriving the LPC features from all the extracted voiced sequences, and used for classification. The isolated words chosen based on the phonemes are associated with the extracted features to establish classification system input-output mapping. The data are then normalized and randomized to rearrange the values into definite range. The Multilayer Neural Network (MLNN) model has been developed with four combinations of input and hidden activation functions. The neural network models are trained with 60%, 70% and 80% of the total data samples. The neural network architecture was aimed at creating a robust model with 60%, 70%, and 80% of the feature set with 25 trials. The trained network model is validated by simulating the network with the remaining 40%, 30%, and 20% of the set. The reliability of trained network models were compared by measuring true-positive, false-negative, and network classification accuracy. The LPC features show better discrimination and the MLNN neural network models trained using the LPC spectral band features gives better recognition. [ABSTRACT FROM AUTHOR]

An artificial neural network (ANN) based methodology to diagnose transformer faults is proposed. The synthetic minority over-sampling technique (SMOTE) is used to solve the imbalance in the dataset. The SMOTE is improved by introducing a full cycle of creating synthetic samples from minority class samples for the goals that the over-sampled ratio can be automatically determined and the sample size of each category can be completely consistent. The contents of dissolved gases in transformer oils are treated as the original features. The optimal features combination for ANN is determined by comparing the performances of the ANN when different feature combinations are used. The performances of different activation functions used in the ANN are investigated to give the optimal one. The tested results show the high accuracy (97.92%) of the proposed methodology if the optimum feature combination and activation function are used. [ABSTRACT FROM AUTHOR]

In this paper, we have proposed a novel traffic sign recognition algorithm based on sparse representation and dictionary learning. In the past period of research and applications of traffic sign recognition, most of the traffic sign recognition algorithms are based on statistical learning, neural networks and template matching algorithm. In these algorithms, they need high-dimensional mapping during classification, resulting in huge amount of calculation. Meanwhile, when the external environment changes, such as illumination, deformation and occlusion, the recognition rate will be further reduced. The proposed sparse representation theory has much better performance to solve the problems of external environment changed and while we use dictionary learning method to build a traffic sign over-complete redundant dictionary, the experimental results clearly showed that the algorithm we proposed has much better performance than traditional algorithm and also has much higher recognition rates. [ABSTRACT FROM AUTHOR]

In this paper, we present a new algorithm for learning evaluation functions of the game of Go. Recently AlphaGo Zero and AlphaZero have shown that accurate evaluation functions can be constructed by using deep neural networks. Such a training, however, requires an enormous amount of computational resources that are not available for most researchers. One of the next challenges in this domain is constructing accurate evaluation functions with lesser computational resources. To tackle this problem, we apply the RankNet algorithm to training an AlphaGo Zero style unified Policy and Value network in a learning-to-rank fashion. Using the pairwise RankNet training increases the potential number of training examples and alleviates the requirements for the number of game records. Our modified RankNet algorithm trains both value and policy losses and its joint training makes the learning stable. Experimental results showed that neural networks trained by our algorithm showed higher playing strength than other methods, especially when the dataset sizes were relatively limited. [ABSTRACT FROM AUTHOR]

In this paper, the prediction of damage results for complex network is considered under grey information attack. Firstly, in order to construct more realistic networks, a new algorithm is proposed to generate 3 types of fully connected networks (normal scale-free network, scale-free network with cutoff, random network). Secondly, robustness of the 3 networks is analyzed under grey information attack. And then, a new method is proposed to predict the damage results by training the BP neural network. Thirdly, the effects of different topological parameters on the damage results are analyzed and a new method is proposed to find central nodes of the network. Finally, the damage results of a real bus network under grey information attack are predicted by the proposed method and several suggestions are given to help protect the real bus network. [ABSTRACT FROM AUTHOR]

Background: Detection of clustered microcalcification (MC) from mammograms plays essential roles in computer-aided diagnosis for early stage breast cancer.Objective: To tackle problems associated with the diversity of data structures of MC lesions and the variability of normal breast tissues, multi-pattern sample space learning is required.Methods: In this paper, a novel grouped fuzzy Support Vector Machine (SVM) algorithm with sample space partition based on Expectation-Maximization (EM) (called G-FSVM) is proposed for clustered MC detection. The diversified pattern of training data is partitioned into several groups based on EM algorithm. Then a series of fuzzy SVM are integrated for classification with each group of samples from the MC lesions and normal breast tissues.Results: From DDSM database, a total of 1,064 suspicious regions are selected from 239 mammography, and the measurement of Accuracy, True Positive Rate (TPR), False Positive Rate (FPR) and EVL = TPR* 1-FPR are 0.82, 0.78, 0.14 and 0.72, respectively.Conclusion: The proposed method incorporates the merits of fuzzy SVM and multi-pattern sample space learning, decomposing the MC detection problem into serial simple two-class classification. Experimental results from synthetic data and DDSM database demonstrate that our integrated classification framework reduces the false positive rate significantly while maintaining the true positive rate. [ABSTRACT FROM AUTHOR]

Background: Although Pneumatic Artificial Muscle (PAM) has a promising future in rehabilitation robots, it's difficult to realize accurate position control due to its highly nonlinear properties.Objective: This paper deals with position control of PAM.Methods: To describe the hysteresis inside PAM, a polynomial based phenomenological function is developed. Based on the phenomenological model for PAM and analysis of pressure dynamics within PAM, an adaptive cascade controller is proposed. Both outer loop and inner loop employ BP Neural Network tuned PID algorithm. The outer loop is to handle high nonlinearities and unmodeled dynamics of PAM, while the inner loop is responsible for nonlinearities caused by pressure dynamics.Results: Experimental results show high tracking accuracy as compared with a convention PID controller.Conclusion: The proposed controller is effective in improving performance of PAM and will be implemented in a rehabilitation robot. [ABSTRACT FROM AUTHOR]

This paper presents a multi-class Support Vector Machine (SVM) based algorithm for on-line static security assessment of the power systems. The proposed SVM based security assessment algorithm has a very small training time and space in comparison with the traditional machine learning methods such as Artificial Neural Networks (ANN) based algorithms. In addition, the proposed algorithm is faster than existing algorithms. One of the main points, to apply a machine learning method is feature selection. In this paper, a new Decision Tree (DT) based feature selection algorithm has been presented. The proposed SVM algorithm has been applied to New England 39-bus power system. The simulation results show the effectiveness and the stability of the proposed method for on-line static security assessment. The effectiveness of the proposed feature selection algorithm has been investigated, too. The proposed feature selection algorithm has been compared with different feature selection algorithms. The simulation results demonstrate the effectiveness of the proposed feature algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a visual speech recognition technique using facial movement video. The acoustic signals of consonants are often confusing in noisy environments. To overcome this shortcoming, the focus of this paper is identifying consonants using visual information. This paper investigates the feasibility of using facial movements to identify phonemes. The proposed approach adopts a visual speech model based on the viseme model of the Moving Picture Experts Group 4 (MPEG-4) standard. It is a movement-based system, and the facial movements are segmented from the video using an accumulative image subtraction method that results in a 2-D grayscale motion history image (MHI). The MHI is classified using a combination of the discrete stationary wavelet transform (SWT) and image moments (Hu moments, geometric moments and Zernike moments). Feedforward multilayer perceptron (MLP) neural networks with backpropagation (BPN) learning algorithm are used to classify the features to investigate the performance of the three moment features. The experimental results indicate that Zernike moments have better representation ability and provide rotational invariant property for the proposed application. The results also demonstrate that the proposed technique can identify consonants reliably using the viseme model of MPEG-4 standard with a recognition rate of 85%. [ABSTRACT FROM AUTHOR]

The combination of machine learning and artificial intelligent has already proved its potential in achieving remarkable results for modeling unknown systems. These techniques commonly use enough data samples to train and optimize their architectures. In the present era, with the availability of enough storage and computation power, the machine learning based data-driven system modeling approaches are getting popular as they do not interrupt the normal system operations and work solely on collected data. This work proposes a data-driven parametric neural network technique for modeling time-delayed systems, which is demanding but challenging area of research and comes under nonlinear optimization problem. The key contribution of this work is the inclusion of an extended B-polynomial into the network structure for estimating time-delayed first and second order system models. These type of models extensively used for addressing simulations, predictions, controlling and monitoring related issues. Also, an adaptive learning based convergence of the proposed algorithm is proved with the help of the Lyapunov stability theory. The proposed algorithm compared with existing techniques on some well-known example problems. A real practical system plant is also included for validating the proposed concept. [ABSTRACT FROM AUTHOR]

The semi-supervised learning (SSL) problems are often solved by graph based algorithms, semi-definite programmings etc. These methods always require high space complexities, and thus are not efficient for network intrusion detection systems. Apart from the space complexity challenge, a network intrusion detection system should be able to handle the distribution drifting of data flow as well. A common solution for this concept drift problem is by SSL. In this paper, an incremental SSL training framework is proposed to combine the low space complexity advantage of topology learning and SSL for network intrusion detection. First, the unsupervised self-organizing incremental neural network is extended to process labeled and unlabeled information incrementally. Second, a kernel function is constructed from the training results of the previous step. Finally, a kernel machine is trained with the constructed kernel function. The proposed method reduces the space complexity of SSL to the magnitude similar to supervised learning. The experiments are carried out on the NSL-KDD datasets, and the results show that the proposed method outperforms the mainstream methods such as Transductive Support Vector Machine and Label Propagation. [ABSTRACT FROM AUTHOR]

A modified version of Boosted Mixture of Experts (BME) for low-resolution face recognition is presented in this paper. Most of the methods developed for low-resolution face recognition focused on improving the resolution of face images and/or special feature extraction methods that can deal effectively with low-resolution problem. However, we focused on the classification step of face recognition process in this paper. Using Neural Networks (NN) combinations is an efficient approach to deal with complex classification problems, such as the low-resolution face recognition which involves high-dimensional feature sets and highly overlapped classes. Mixture of Experts (ME) and boosting methods are two of the most popular and interesting NN combining methods, which have great potential for improving performance in classification. A modified combining approach based on both features of ME and boosting is presented in order to deal with this complex classification problem efficiently. Previous works [1,2] made attempts to incorporate the complementary features of boosting method in ME training algorithm to boost the performance. These approaches called Boosted Mixture of Experts (BME) have some drawbacks. Based on the analysis of the problems of previous approaches, some modifications are suggested in this paper. A modification in the pre-loading (initialization) procedure of ME is proposed to address the limitations of previous approaches and overcome them using a two stages pre-loading procedure. In our suggested approach, both the error and confidence measures are used as the difficulty criteria in boosting-based partitioning of the problem space. Regarding the nature of this approach, we call the proposed method Boosted Pre-loaded Mixture of Experts (BPME). The proposed method is tested in a low-resolution face recognition problem and compared to the other variations of ME and boosting method. The experiments are conducted using low-resolution variations of two common face databases including the ORL and Yale databases. The experimental results show that BPME method has significant better recognition rates against the other compared combining methods in various tested conditions including different quality grades of face images and different sizes of the training set. [ABSTRACT FROM AUTHOR]

Multi-modal image fusion techniques aid the medical experts in better disease diagnosis by providing adequate complementary information from multi-modal medical images. These techniques enhance the effectiveness of medical disorder analysis and classification of results. This study aims at proposing a novel technique using deep learning for the fusion of multi-modal medical images. The modified 2D Adaptive Bilateral Filters (M-2D-ABF) algorithm is used in the image pre-processing for filtering various types of noises. The contrast and brightness are improved by applying the proposed Energy-based CLAHE algorithm in order to preserve the high energy regions of the multimodal images. Images from two different modalities are first registered using mutual information and then registered images are fused to form a single image. In the proposed fusion scheme, images are fused using Siamese Neural Network and Entropy (SNNE)-based image fusion algorithm. Particularly, the medical images are fused by using Siamese convolutional neural network structure and the entropy of the images. Fusion is done on the basis of score of the SoftMax layer and the entropy of the image. The fused image is segmented using Fast Fuzzy C Means Clustering Algorithm (FFCMC) and Otsu Thresholding. Finally, various features are extracted from the segmented regions. Using the extracted features, classification is done using Logistic Regression classifier. Evaluation is performed using publicly available benchmark dataset. Experimental results using various pairs of multi-modal medical images reveal that the proposed multi-modal image fusion and classification techniques compete the existing state-of-the-art techniques reported in the literature. [ABSTRACT FROM AUTHOR]

Aiming at the precocious convergence, low search accuracy and easy divergence of most particle swarm optimizations with velocity terms, a particle swarm optimization (IWPSO) with random inertia weights and quantization is proposed. First, the inertia weights are obeyed to be distributed randomly, and the learning factors are adjusted asynchronously to optimize the parameters in BP network. Secondly, BP network is trained using the IWPSO algorithm based on the sample data. Finally, simulation experiments prove that the algorithm has significantly improved search speed, convergence accuracy, and stability compared with existing improved algorithms. Due to the characteristics of IWPSO algorithm, the BP neural network optimized by IWPSO has better global convergence performance and is an efficient particle swarm optimization. [ABSTRACT FROM AUTHOR]

BACKGROUND: Nowadays, the growth of smart cities is enhanced gradually, which collects a lot of information and communication technologies that are used to maximize the quality of services. Even though the intelligent city concept provides a lot of valuable services, security management is still one of the major issues due to shared threats and activities. For overcoming the above problems, smart cities' security factors should be analyzed continuously to eliminate the unwanted activities that used to enhance the quality of the services. OBJECTIVES: To address the discussed problem, active machine learning techniques are used to predict the quality of services in the smart city manages security-related issues. In this work, a deep reinforcement learning concept is used to learn the features of smart cities; the learning concept understands the entire activities of the smart city. During this energetic city, information is gathered with the help of security robots called cobalt robots. The smart cities related to new incoming features are examined through the use of a modular neural network. RESULTS: The system successfully predicts the unwanted activity in intelligent cities by dividing the collected data into a smaller subset, which reduces the complexity and improves the overall security management process. The efficiency of the system is evaluated using experimental analysis. CONCLUSION: This exploratory study is conducted on the 200 obstacles are placed in the smart city, and the introduced DRL with MDNN approach attains maximum results on security maintains. [ABSTRACT FROM AUTHOR]

The paper contains a description of the implementation and performance evaluation of the agent-based population learning algorithm used to train the feed-forward artificial neural networks. The goal of the research was to evaluate efficiency of the agent-based approach and to establish experimentally which different factors representing the A-Team structure and topology affect the performance of the analyzed agent-based algorithm. The paper includes a general overview of the JABAT environment used to deploy the ANN training algorithm, a description of different agents employed and their roles, as well as the computational experiment plan and the discussion of the performance evaluation results. [ABSTRACT FROM AUTHOR]

Spiking neural P systems simulate the behavior of neurons sending signals through axons. Recently, some applications concerning Boolean circuits and sorting algorithms have been proposed. In this paper, we study the ability of such systems to simulate a well known parallel sorting model, sorting networks. First, we construct spiking neural P systems which act as comparators of two values, and then show how to assemble these building blocks according to the topology of a sorting network of N values. In the second part of the paper, we formalize a framework to transform any sorting network into a network composed of comparators which sort n values, 2 < n < N, having the same behaviour as the original sorting network, but using fewer neurons and synapses than the direct simulation. A comparison between the two models proposed here and the sorting model of Ionescu and Sburlan is also given. [ABSTRACT FROM AUTHOR]

In this paper, a Group Method of Data Handling (GMDH)-type neural network algorithm with a feedback loop for structural identification of Radial Basis Function (RBF) neural network is proposed. In case of the GMDH-type neural network, the network architecture is automatically organized by heuristic self-organization. Optimum architecture is evolved using one of the criterions, defined as Akaike's Information Criterion (AIC) or Prediction Sum of Squares (PSS), for minimizing the prediction error. In the conventional multilayered neural network, prediction error criteria defined as AIC and PSS cannot be used to determine the neural network architecture. In case of the GMDH-type neural network proposed in this paper, structural parameters such as the number of neurons, relevant input variables and the number of feedback loop calculations are automatically determined so as to minimize AIC or PSS. Furthermore, the GMDH-type neural network can identify RBF neural network accurately, since the complexity of the neural network is increased gradually by feedback loop calculations. [ABSTRACT FROM AUTHOR]

This paper is concerned with robust control of a quad-rotor aerial vehicle attitudes (pitch, roll, yaw). Attitudes of the quad-rotor vehicle is affected by various sources of disturbances such as wind and ground effect. In this paper, we propose a new disturbance observer so that these disturbances are estimated and compensated by the disturbance observer. It is shown by simulations that the proposed disturbance observer effectively compensates disturbances. [ABSTRACT FROM AUTHOR]

Development of a robust triple multimodal biometric approach for human authentication using fingerprint, iris and voice biometric is the main objective of this manuscript. Accordingly, three essential algorithms for biometric authentication are presented. The extracted features from these multimodals are combined via feature fusion center (FFC) and feature scores. These features are trained through artificial neural network (ANN) and support vector machine (SVM) classifiers. The first algorithm depends on boundary energy method (BEM) extracted features from fingerprint, normalized combinational features from iris and dimensionality reduction methods (DRM) from voice using sum/average FFC. The second proposed algorithm uses extracted features from zoning method of fingerprint, SIFT of iris and higher order statistics (HOS) of voice signals. The third proposed algorithm consists of extracted features from zoning method for fingerprint, SIFT from iris and DRM from voice signals. Classification accuracy of implemented algorithms is estimated. Comparison between proposed algorithms is introduced in terms of equal error rate (EER) and ROC curves. The experimental results confirm superiority of second proposed algorithm which achieves a classification rate of 100% using SVM classifier and sum FFC. From computational point of view, the first algorithm consumes the lowest time using SVM classifier. On other hand, the lowest EER is achieved by first proposed algorithm for extracted features from Karhunen-Loeve transform (KLT) method of DRM. Additionally, the lowest ROC curves are accomplished respectively for extracted features from multidimensional scaling (MDS), generated ARMA synthesis and Isomap features. Their accuracy is improved with SVM. Also, the sum FFC introduces efficient results compared to average FFC. These algorithms have the advantages of robustness and the strength of selecting unimodal, double and triple biometric authentication. The obtained results accomplish a remarkable accuracy for authentication and security within multi practical applications. [ABSTRACT FROM AUTHOR]

The development in science and technical intelligence has incited to represent an extensive amount ofdata from various fields of agriculture. Therefore an objective rises up for the examination of the available data and integrating with processes like crop enhancement, yield prediction, examination of plant infections etc. Machine learning has up surged with tremendous processing techniques to perceive new contingencies in the multi-disciplinary agrarian advancements. In this pa- per a novel hybrid regression algorithm, reinforced extreme gradient boosting is proposed which displays essentially improved execution over traditional machine learning algorithms like artificial neural networks, deep Q-Network, gradient boosting, ran- dom forest and decision tree. Extreme gradient boosting constructs new models, which are essentially, decision trees learning from the mistakes of their predecessors by optimizing the gradient descent loss function. The proposed hybrid model performs reinforcement learning at every node during the node splitting process of the decision tree construction. This leads to effective utilizationofthesamplesbyselectingtheappropriatesplitattributeforenhancedperformance. Model'sperformanceisevaluated by means of Mean Square Error, Root Mean Square Error, Mean Absolute Error, and Coefficient of Determination. To assure a fair assessment of the results, the model assessment is performed on both training and test dataset. The regression diagnostic plots from residuals and the results obtained evidently delineates the fact that proposed hybrid approach performs better with reduced error measure and improved accuracy of 94.15% over the other machine learning algorithms. Also the performance of probability density function for the proposed model delineates that, it can preserve the actual distributional characteristics of the original crop yield data more approximately when compared to the other experimented machine learning models. [ABSTRACT FROM AUTHOR]

Background: In recent times there has been a significant change in lifestyle in many parts of the world, with most people experiencing a more sedentary existence combined with an abundance of food. This has resulted in the modern epidemic of obesity and consequent hyperinsulinemia - situations which in women may precipitate expression of fertility problems; effective methods to evaluate the fertility status are required. Ultrasonographic imaging is an effective, easy to use, safe, and readily available noninvasive means to evaluate fertility potential.Objective: Manual recognition of the follicles in terms of area measurement and counting the number of follicles is laborious; often fatigue may lead to error-prone conclusions. The paper attempts an automated classification of the ovaries based on the biomarking done by the physician. Also, biomarked data correlates with the hormones values such as androgen, testosterone and leutinizing hormone.Methods: Despeckled images are segmented by improved active contour with split-Bregman optimization. The features are extracted from images using geometric and intensity method. The significant features selected by particle swarm optimization and dimension reduction by principal component analysis and classification by probabilistic neural network.Results: Proposed probabilistic neural network achieves maximum efficiency of 97% compared to SVM 92% and RBF 88%.Conclusions: The results obtained show that using a very large number of features combined with a feature selection approach allows us to achieve high classification rates. [ABSTRACT FROM AUTHOR]

In this article, a new methodology, hybrid genetic algorithm GA, algorithm SPEA/R with Deep Neural Network (HDNN&SPEA/R). This combination gave computing time much faster than computing time when using genetic algorithms SPEA/R. On the other hand, this combination also significantly reduces the number of samples needed for the training of deep artificial neural networks. This is the task of finding out an optimal set that changes with the engine velocity of multi-objective optimization involving 12 simultaneous optimization goals: proportional P, integral I, derivative D, additional integration n and differentiation orders m factor, displacement amplification coefficient KDloop, acceleration amplification coefficient KAloop in two controllers acceleration and displacement to enhance the ride comfort. This article has provided a control algorithm of a Cascade FOPID controller to control the acceleration and displacement of the mount. Besides, the article also offers solutions to optimize the 12 simultaneous parameters of the two controllers by the new hybrid method HDNN&SPEA/R and suitable for the speed of rotation of the engine. To increase the safety factor in operation, we use magnetorheological dampers (MR) in a powertrain mounting system and a continuous state damper controller that calculates the input voltage to the damper coil. The results of this control method are compared with traditional PID systems, optimal PID parameter adjustment using genetic algorithms (GA) and passive drive system mounts. The results are tested in both time and frequency domains, to verify the success of the proposed Cascade FOPID algorithm. The results show that the proposed Cascade FOPID controller of the MR engine mounting system gives very good results in comfort and softness when riding compared to other controllers. This proposal has reduced 335 hours for optimal computation time and reduce vibration a lot. [ABSTRACT FROM AUTHOR]

Using Chaotic characteristics of dynamic system is a promising direction to design cryptosystems that play a pivotal role in a very important engineering application of cognitive informatics, i.e., information assurance and security. However, encryption algorithms based on the lowdimensional chaotic maps face a potential risk of the keystream being reconstructed via return map technique or neural network method. In this paper, we propose a new digital image encryption algorithm that employs a hyper-chaotic cellular neural network. To substantiate its security characteristics, we conduct the following security analyses of the proposed algorithm: key space analysis, sensitivity analysis, information entropy analysis and correlation coefficients analysis of adjacent pixels. The results demonstrate that the proposed encryption algorithm has desirable security properties and can be deployed as a cornerstone in a sound security cryptosystem. The comparison of the proposed algorithm with five other chaos-based image encryption algorithms indicates that our algorithm has a better security performance. [ABSTRACT FROM AUTHOR]

The paper provides an alternative approach to protein structural class prediction employing artificial neural network. Existing works on protein structural class prediction are computationally intensive. The method employs SOFM for extraction of representative feature vectors, for the four different structural classes and then uses Principal Component Analysis for finding optimum feature vector dimension. Nearest neighborhood classification technique is finally utilised; to classify these protein datapoints to their respective classes. The proposed work presented in this paper, maintains the same level of classification accuracy in minimum computation time, as it employs most prominent and reduced number of feature set for classification. [ABSTRACT FROM AUTHOR]

This paper describes a new approach for predicting tertiary structure of protein using artificial neural network and particle swarm optimization technique. The paper is concetrated around the well known Ab-initio approach for global minimisation of energy function. It predicts the native structure of protein by finding the main chain dihedral angles; through the optimization of CHARMM energy function, using particle swarm optimization algorithm. Side chain dihedral angle are predicted using three layered artificial neural network, realised with back propagation algorithm. This approach has merit as it reduces the dimensionality of the search space and computationally outperforms all other classical technique in atleast 80% cases. [ABSTRACT FROM AUTHOR]

Active Noise Control (ANC) system is commonly designed and implemented using adaptation algorithm and adaptive control structure. In this paper we present theoretical and experimental result of active noise control system using Recurrent Fuzzy Neural Network (RFNN). RFNN is developed by combining fuzzy logic and neural networks, aimed at producing better control system performance than if we use neural network or fuzzy logic separately. Using a control structure with two multilayer feedforward RFNNs (one RFNN serves as a nonlinear controller while the other one operates as a nonlinear plant model), a recursive least-squares algorithm based on Adjoint Extended Kalman Filter approach is employed for the training of the controller network. Extended Kalman Filter (EKF) algorithm is introduced to develop a new algorithm with faster convergence speed by using nonlinear recursive-least square method. Experimental result using DSP demonstrates effectiveness of the proposed RFNN structure and algorithm to attenuate unwanted noise. [ABSTRACT FROM AUTHOR]

A new algorithm based on wavelet packet transform and singular value decomposition is proposed in this paper for classification of textures in the presence of noise. Lower singular values are affected more by noise than higher singular values, and hence only higher singular values are used to classify textures in the presence of noise. The probability density function of the selected singular values is then modeled as an exponential distribution, and the model parameter for the distribution is estimated using the maximum likelihood estimation technique. The model parameter, one for each subband is used as features for the classification. The classification is carried out using Weighted Probabilistic Neural Networks (WPNN). Compared to conventional probabilistic neural networks, WPNN includes weighting factors between pattern layer and summation layer of the conventional PNN. Performance of the algorithm is compared with `wavelet domain generalized Gaussian density based model' in terms of signal to noise ratio and classification rate. Experimental results prove that the proposed algorithm achieves better classification rate under noisy environment. [ABSTRACT FROM AUTHOR]

This paper presents some studies in biologically inspired computing. The case studies are grouped under two sections, in the first section case studies involving more fundamental aspects of networks and in the second section application oriented studies are presented. The first section involves geometrical interpretation of back propagation networks and a scheme for generating network structure from the decision space was offered. The second study presents a new encoding scheme and also studies how the encoding scheme and performance are related. The third study is specific to Hopfield neural networks and shows that a stiffness matrix has properties which allow it being mapped to the Hopfileld transition matrix. The last study presents the particle swarming algorithm and a new concept of quantum inspired computing. The second section involves cases relating to some engineering applications or bench marks of some biologically inspired computing. The case studies as many of them based on manipulation of engineering structures, this section presents a stiffness matrix of a simple spring attached on a 3D body. The following study involves manipulation of matrix elements in order to achieve vibration decoupling (of modes). This is studied in three different ways; firstly an analytical solution is obtained. This way, the equations were proved to be ill conditioned. The second study involves using these equations with GA algorithm which showed that GA is robust in dealing with ill conditioned problems and finally it was assumed no prior knowledge of the matrix formulation. In this case GA operated directly with the mode shapes obtained from the eigenvector analysis. The final approach appears to be the most unreliable in convergence. The matrix formulation was also used with Hopfield networks. The other examples included gearbox fault detection which as well as identifying the faults the study demonstrated the importance of preprocessing and information filtering or refinement. Furthermore the studies on gear box faults showed that even the type of preprocessing influences the performance of identification. The study of fault identification in gas cylinders led recognition of various loopholes in manually selection of features for fault identification. The study involved manual feature extraction which in this case led to endless experiments, however the use of the frequency response function (FRF) proved to be the most effective in this case and probably it is likely to be the same for similar cases where the system disturbance levels cannot be repeated. The last case study involved bench mark based comparative study among GA, PSO and quantum inspired computing. This study showed that all three are similar in their effectiveness but quantum inspired computing algorithm showed an incredibly fast convergence during the first few cycles of optimization. A series of less detailed cases such as cellular automata for breast cancer growth modeling, the use of GA in real time control, were also included in the paper. The paper, finally weighs findings against the No Free Lunch (NLF) theorem, although conclusions are complimentary. The work presented illustrates the reliance of biologically inspired computing to representation and encoding schemes both for architecture and data for its effective execution. [ABSTRACT FROM AUTHOR]

Hierarchical fuzzy neural networks can use less rules to model nonlinear system with high accuracy. But the normal training method for hierarchical fuzzy neural networks is very complex. In this paper we modify the backpropagation approach and employ a time-varying learning rate that is determined from input-output data and model structure. Stable learning algorithms for the premise and the consequence parts of the fuzzy rules are proposed. The calculation of the learning rate does not need any prior information such as estimation of the modeling error bounds. The new algorithms are very simple, we can train each sub-block of the hierarchical fuzzy neural networks independently. [ABSTRACT FROM AUTHOR]

Evolutionary Engineering (EE) is defined to be “the art of using evolutionary algorithms approach such as genetic algorithms to build complex systems”. This paper deals with a neural net based system. It analyses ability of genetically trained neural nets to control Simulated robot arm, witch tries to track a moving object. In difference from classical Approaches neural network learning is performed on line, i.e., in real time. Usually systems are built/evolved, i.e., genetically trained separately of their utilization. That is how it is commonly done. It's a fact that evolution process is heavy on time; that's why Real‐Time approach is rarely taken into consideration. The results presented in this paper show that such approach (Real‐Time EE) is possible. These successful results are essentially due to the “continuity” of the target's trajectory. In EE terms, we express this by the Neighbourhood Hypothesis (NH) concept. [ABSTRACT FROM AUTHOR]

This paper presents a new model of an artificial neural network solving classification problems, called Local Transfer Function Classifier (LTF-C). Its architecture is very similar to this of the Radial Basis Function neural network (RBF), however it utilizes an entirely different learning algorithm. This algorithm is composed of four main parts: changing positions of reception fields, changing their sizes, insertion of new hidden neurons and removal of unnecessary ones during the training. The paper presents also results of LTF-C application to three real-life tasks: handwritten digit recognition, credit approval and cancer diagnosis. LTF-C was able to solve each of these problems with better accuracy than most popular classification systems. Moreover, LTF-C was relatively small and fast. [ABSTRACT FROM AUTHOR]

In this paper we show that for every k-block morphism (k ≥ 2) there is a spiking neural P system which computes the morphism. This result generalises the result explored by G. Păun, M. Pérez-Jiménez, and G. Rozenberg. We give an algorithm which constructs the spiking neural P system, that is, if a k-block morphism is given as an input, the algorithm makes rules of the spiking neural P system which computes the morphism. [ABSTRACT FROM AUTHOR]

There has been a considerable effort in the design of evolutionary systems for the automatic generation of neural networks. Symbiotic Adaptive Neuro Evolution (SANE) is a novel approach that carries co-evolution of neural networks at two levels of neuron and network. The SANE network is likely to face problems when the applied data set has high number of attributes or a high dimensionality. In this paper we build a modular neural network with probabilistic sum integration technique to solve this curse of dimensionality. Each module is a SANE network. The division of the problem involves the breaking up of the problem into sub-problems with different (may be overlapping) attributes. The algorithm was simulated for the Breast Cancer database from UCI machine learning repository. Simulation results show that the algorithm, keeping the dimensionality low, was able to effectively solve the problem. [ABSTRACT FROM AUTHOR]

Evolution strategies with q-Gaussian mutation, which allows the self-adaptation of the mutation distribution shape, is proposed for dynamic optimization problems in this paper. In the proposed method, a real parameter q, which allows to smoothly control the shape of the mutation distribution, is encoded in the chromosome of the individuals and is allowed to evolve. In the experimental study, the q-Gaussian mutation is compared to Gaussian and Cauchy mutation on experiments generated from the simulation of evolutionary robots and on dynamic optimization problems generated by the Moving Peaks generator. [ABSTRACT FROM AUTHOR]

In this paper, a model-free approach for data mining in engineering is presented. The numerical approach is based on artificial neural networks. Recurrent neural networks for fuzzy data are developed to identify and predict complex dependencies from uncertain data. Uncertain structural processes obtained from measurements or numerical analyses are used to identify the time-dependent behavior of engineering structures. Structural action and response processes are treated as fuzzy processes. The identification of uncertain dependencies between structural action and response processes is realized by recurrent neural networks for fuzzy data. Algorithms for signal processing and network training are presented. The new recurrent neural network approach is verified by a fuzzy fractional rheological material model. An application for the identification and prediction of time-dependent structural behavior under dynamic loading is presented. [ABSTRACT FROM AUTHOR]

In this paper an active random noise control using adaptive learning rate neural networks with an immune feedback law is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased in proportion to its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without inducing oscillation. In the proposed method, because an immune feedback law is changing the learning rate of the neural networks individually and adaptively, it is expected that the neural cost function will reach its minimum rapidly, resulting in a reduced training time. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed to validate the convergence properties of the method. Control results show that the adaptive learning rate neural network control structure can outperform linear controllers and conventional neural network controllers for active random noise control. [ABSTRACT FROM AUTHOR]

This paper discusses an algorithm that provides a way to obtain ensembles of collaborating artificial neural networks (ANNs) online. That is, its purpose is to find solutions to problems based on the interaction of sets of, in principle, heterogeneous ANNs whose joint behaviour results in an emergent solution. This approach is intrinsically able to handle lifelong adaptation within the society in order to comply with changing situations or demands in dynamic environments. It is called Asynchronous Situated Coevolution (ASiCo) and was designed for the lifelong coevolution of artificial neural network societies. ASiCo deals with the evolutionary part of neuroevolution and it can support any type of neural network structure or even neural network construction mechanism. Consequently, it can be extended with some of the techniques found in single ANN neuroevolutionary mechanisms when considering the simultaneous evolution of network weights and network topology. The operation and characteristics of this strategy are illustrated through some experiments carried out using a well known benchmark collaboration task. [ABSTRACT FROM AUTHOR]

This paper proposes a Neural Network model using Generalised kernel functions for the hidden layer of a feed forward network. These functions are Generalised Radial Basis Functions (GRBF), and the architecture, weights and node topology are learned through an evolutionary algorithm. The proposed model is compared with the corresponding standard hidden-node models: Product Unit (PU) neural networks, Multilayer Perceptrons (MLP) with Sigmoidal Units (SUs) and the RBF neural networks. The proposed methodology is tested using twelve benchmark classification datasets from well-known machine learning problems. GRBFs are found to perform better than other standard basis functions at the classification task. [ABSTRACT FROM AUTHOR]