Search

Monitoring and managing litter on the roadways is important not only for preserving the cleanliness and esthetic appeal of our cities but also for safeguarding the overall health and sanitary environment of citizens. With the development of artificial intelligence, it is now possible to design algorithms capable of autonomously assessing the sanitation status of roadways. In this paper, we propose a method for detecting garbage on roads as our solution to tackle the issue. The proposed model is a deep learning model with an attention mechanism introduced to detect garbage in real-time scenarios. Furthermore, the object recognition capability of the model is enhanced through transfer learning to mitigate the influence of irrelevant content during training. The refined network can detect rubbish on roads with higher efficiency than the existing models. Also, compared with other methods, it consumes less amount of data for training. The experimental results demonstrate the efficiency of our proposed model, with a performance boost of 7.62% over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Model pruning is one of the main methods of deep neural network model compression. However, the existing model pruning methods are inefficient, there is still a lot of redundancy in the network, and the pruning has a great impact on the accuracy. In addition, the traditional pruning process usually needs to fine-tune the network to restore accuracy, and fine-tuning has a limited effect on accuracy recovery, so it is difficult to achieve a high level of accuracy. In this paper, we propose a new neural network pruning framework: the channel sparsity is realized by introducing a scale factor, and the sparse network is pruned by setting a global threshold, which greatly improves the efficiency of pruning. After pruning, this paper proposes a rewind method to restore the accuracy, that is, save the weight after training, and then reload it on the network for training to restore the accuracy. In addition, we also study the best rewind point of the three networks. The experimental results show that our method significantly reduces the number of parameters and FLOPs without affecting or even improving the accuracy, and the rewind method proposed by us achieves a better accuracy recovery effect than fine-tuning. At the same time, we find that the epoch with the highest accuracy is the best rewind point, and the accuracy is the highest after saving its corresponding weight and retraining the model. [ABSTRACT FROM AUTHOR]

EEG has been proved to be an effective tool for researchers' cognition and mental workload by detecting the changes of brain activity potential. The mental workload of pilots in aviation flight is closely related to the characteristics of flight tasks. The previous methods have problems such as lack of objectivity, low EEG analysis ability and lack of real-time analysis ability. In order to solve these problems, this paper proposes a multi-dimensional data fusion brain workload calculation method based on flight effect evaluation, which integrates vision, operational behavior and visual gaze, and classifies and analyzes them in combination with EEG data. This method evaluates the mental workload of pilots from three aspects: visual gaze behavior, control behavior and flight effect in the simulated flight experimental environment, and realizes a more objective mental workload analysis. Then, the synchronously collected EEG data are segmented and sampled to form a dataset, and an LSTM neural network model integrating attention mechanism is established, in which the attention mechanism is used to improve the feature processing ability of the network model for the classification of complex EEG data. After machine learning training, the final model can achieve 94% detection accuracy for 2-s EEG data, and has the ability of real-time analysis in the application environment. Compared with the previous similar LSTM model, the accuracy is improved by 6%, which also shows the effectiveness of the model. [ABSTRACT FROM AUTHOR]

In the resource-constrained embedded systems, the designing of efficient deep neural networks is a challenging process, due to diversity in the artificial intelligence applications. The quantization in deep neural networks superiorly diminishes the storage and computational time by reducing the bit-width of networks encoding. In order to highlight the problem of accuracy loss, the quantization levels are automatically discovered using Policy Feedback-based Reinforcement Learning Method (PF-RELEQ). In this paper, the Proximal Policy Optimization with Policy Feedback (PPO-PF) technique is proposed to determine the best design decisions by choosing the optimum hyper-parameters. In order to enhance the sensitivity of the value function to the change of policy and to improve the accuracy of value estimation at the early learning stage, a policy update method is devised based on the clipped discount factor. In addition, specifically the loss functions of policy satisfy the unbiased estimation of the trust region. The proposed PF-RELEQ effectively balances quality and speed compared to other deep learning methods like ResNet-1202, ResNet-32, ResNet-110, GoogLeNet and AlexNet. The experimental analysis showed that PF-RELEQ achieved 20% computational work-load reduction compared to the existing deep learning methods on ImageNet, CIFAR-10, CIFAR-100 and tomato leaf disease datasets and achieved approximately 2% of improvisation in the validation accuracy. Additionally, the PF-RELEQ needs only 0.55 Graphics Processing Unit on an NVIDIA GTX-1080Ti to develop DNNs that delivers better accuracy improvement with fewer cycle counts for image classification. [ABSTRACT FROM AUTHOR]

As a third generation artificial neural network, spiking neuron network is expected to expand the artificial intelligence world. However, as a more detailed simulation of brain, a single run of spiking neural networks (SNNs) simulation can take hours to days. To get a better prediction of SNN simulation performance, existing work requires gathering result of actual runs to conduct accurate modeling. In this paper, we propose a nonempirical SNN simulation performance prediction method, prototyped in a hybrid CPU-FPGA cluster. Experiments show that our method, without actual simulation run, can get comparable accuracy with orders of magnitude less runtime cost. [ABSTRACT FROM AUTHOR]

When using deep learning methods to model natural language, a recurrent neural network that can map input sequences to output sequences is usually used. Considering that natural language contains more complicated syntactic structures, and the performance of cyclic neural networks in long sentence processing will decrease, scholars have introduced an attention mechanism into the model, which has improved the above problems to a certain extent. The existing attention mechanism still has some shortcomings, such as the inability to explicitly obtain the known syntactic structure information in the sentence, and the poor interpretability of the output probability. In response to the above problems, this article will improve the attention mechanism in the recurrent neural network model. Firstly, the prior information in the natural language sequence is constructed as a graph model through syntactic analysis and other means, and then the graph structure regularization term is introduced into the sparse mapping. A new function netmax is constructed to replace the softmax function in the traditional attention mechanism, thereby improving the performance of the model and making the degree of association. The input values corresponding to larger input samples are closer, making the output of the attention mechanism easier to understand. The innovation of this paper mainly lies in that the weight calculation method which can be widely used in the attention mechanism is proposed by combining the deep learning model with statistical knowledge, which opens a channel to introduce the prior information for the deep learning model in natural language processing tasks. [ABSTRACT FROM AUTHOR]

The ultimate direction of intelligent vehicle management is to achieve artificial intelligence (AI), and data mining is an important supporting technology for AI. The adoption of new AI technology can effectively improve operational efficiency and safety, especially in terms of performance. This paper takes the researches on traffic jam as an example and proposes one algorithm for combination forecasting model based on a segmentation algorithm for traffic flow sequence and BP neural network prediction. In this paper, it also introduces the traffic flow clustering analysis and mining algorithms for congestion events at the intersections. The blocking point algorithm is improved, and experimental analysis is performed through samples. Experimental results show that the algorithm use for combination forecasting model can greatly improve the real-time performance of short-term traffic flow prediction and significantly reduce the prediction error rate. Therefore, this algorithm has practical and innovative significance in the field of intelligent vehicle management. [ABSTRACT FROM AUTHOR]

In the era of globalization, manufacturing industries are facing intense pressure to prevent unexpected breakdowns, reduce maintenance cost and increase plant availability. Induction motors are the most sought-after prime movers in modern-day industries due to their robustness. Recently, research has picked up a fervent pace in the area of fault diagnosis of electrical machines. This paper presents the application of Support Vector Machine (SVM) and Artificial Neural Network (ANN)-based system to diagnose the vibration and Instantaneous Power (IP)-based responses of rolling element bearings and broken rotor bars in an induction motor. The dimensionality of the extracted features was reduced using Principal Component Analysis (PCA) and thereafter the selected features were ranked in order of relevance using the Sequential Floating Forward Selection (SFFS) method for reducing the size of input features and finding the most optimal feature set. A comparative analysis of the effectiveness of SVM and ANN is carried out using statistical parameters extracted from vibration and IP signals. The highest accuracy of 92.5% and 98.2% was achieved for vibration and IP signatures, respectively, using the proposed SFFS-based feature selection technique and ANN classification method. The results reveal that ANN has better performance than SVM and the proposed strategy can be used for automatic recognition of machine faults. The use of this type of intelligent system helps in avoiding unwanted and unplanned system shutdowns due to the failure of the motor. [ABSTRACT FROM AUTHOR]

The process of retinal vessel segmentation is important for detection of various eye conditions including the effect of diabetes on eyes, or diabetic retinopathy. As we know, the retinal microvasculature is unique since it is the only part of the human circulation system that can be directly and non-evasively visualized in vivo; readily photographed as well as subjected to digital image analysis. This paper explores a new technique for detecting the idiosyncrasies of retina images, for which we have reviewed some well-known image segmentation algorithms that help in detecting retinal abnormalities. In this work, we have also focused on the extraction of the vessel from retina images and developed an automated diagnostic system for diabetic retinopathy. This paper represents techniques, such as the snake model that was used for auto-extraction of retinal blood vessels and use of wavelet decomposition and back propagation neural network to extract the retinal vessels features and analyze the dataset. Finally, an analysis of performance of the vessel segmentation algorithm and wavelet analysis on standard image databases has been done. In this context, we have used F-score for validation of the result. [ABSTRACT FROM AUTHOR]

With the continuous expansion of the application scope of computer network technology, various malicious attacks that exist in the Internet range have caused serious harm to computer users and network resources. This paper attempts to apply artificial intelligence (AI) to computer network technology and research on the application of AI in computing network technology. Designing an intrusion detection model based on improved back propagation (BP) neural network. By studying the attack principle, analyzing the characteristics of the attack method, extracting feature data, establishing feature sets, and using the agent technology as the supporting technology, the simulation experiment is used to prove the improvement effect of the system in terms of false alarm rate, convergence speed, and false negative rate, the rate reached 86.7%. The results show that this fast algorithm reduces the training time of the network, reduces the network size, improves the classification performance, and improves the intrusion detection rate. [ABSTRACT FROM AUTHOR]

Recent research has demonstrated the effectiveness of deep subspace learning networks, including the principal component analysis network (PCANet) and linear discriminant analysis network (LDANet), since they can extract high-level features and better represent abstract semantics of given data. However, their representation does not consider the nonlinear relationship of data and limits the use of features with nonlinear metrics. In this paper, we propose a novel architecture combining the kernel collaboration representation with deep subspace learning based on the PCANet and LDANet for facial expression recognition. First, the PCANet and LDANet are employed to learn abstract features. These features are then mapped to the kernel space to effectively capture their nonlinear similarities. Finally, we develop a simple yet effective classification method with squared -regularization, which improves the recognition accuracy and reduces time complexity. Comprehensive experimental results based on the JAFFE, CK, KDEF and CMU Multi-PIE datasets confirm that our proposed approach has superior performance not just in terms of accuracy, but it is also robust against block occlusion and varying parameter configurations. [ABSTRACT FROM AUTHOR]

This paper presents an approach for analyzing relationships between data size, cluster, accuracy and diversity in neural network ensembles. The main objective of this research is to find out the influence of data size such as number of patterns, number of inputs and number of classes on various parameters such as clusters, accuracy and diversity of a neural network ensemble. The proposed approach is based on splitting data sets into different groups using the data size, clustering data and conducting training and testing of neural network ensembles. The test data is same for all groups and used to test all trained ensembles. The experiments have been conducted on 15 UCI machine learning benchmark datasets and results are presented in this paper. [ABSTRACT FROM AUTHOR]

This paper presents theoretical and historical backgrounds related to neural network rule extraction. It also investigates approaches for neural network rule extraction by ensemble concepts. Bologna pointed out that although many authors had generated comprehensive models from individual networks, much less work had been done to explain ensembles of neural networks. This paper carefully surveyed the previous work on rule extraction from neural network ensembles since 1988. We are aware of three major research groups i.e., Bologna' group, Zhou' group and Hayashi' group. The reason of these situations is obvious. Since the structures of previous neural network ensembles were quite complicated, the research on the efficient rule extraction algorithm from neural network ensembles was few although their learning capability was extremely high. Thus, these issues make rule extraction algorithm for neural network ensemble difficult task. However, there is a practical need for new ideas for neural network ensembles in order to realize the extremely high-performance needs of various rule extraction problems iu real life. This paper successively explain nature of artificial neural networks, origin of neural network rule extraction, incorporating fuzziness in neural network rule extraction, theoretical foundation of neural network rule extraction, computational complexity of neural network rule extraction, neuro-fuzzy hybridization, previous rule extraction from neural network ensembles and difficulties of previous neural network ensembles. Next, this paper address three principles of proposed neural network rule extraction: to increase recognition rates, to extract rules from neural network ensembles, and to minimize the use of computing resources. We also propose an ensemble-recursive-rule extraction (E-Re-RX) by two or three standard backpropagation to train multi-layer perceptrons (MLPs), which enabled extremely high recognition accuracy and the extraction of comprehensible rules. Furthermore, this enabled rule extraction that resulted in fewer rules than those in previously proposed methods. This paper summarizes experimental results of rule extraction using E-Re-RX by multiple standard backpropagation MLPs and provides deep discussions. The results make it possible for the output from a neural network ensemble to be in the form of rules, thus open the "black box" of trained neural networks ensembles. Finally, we provide valuable conclusions and as future work, three open questions on the E-Re-RX algorithm. [ABSTRACT FROM AUTHOR]

Rainfall-runoff modeling is very important for Water Resources Management because accurate and timely prediction can avoid accidents, such as the life risk, economic losses, etc. This paper proposed the novel hybrid optimization algorithm to combine Neural Network (NN) for rainfall-runoff modeling, namely HGASA-NN. Firstly, a novel and specialized hybrid optimization strategy by incorporating Simulated Annealing algorithm (SA) into Genetic Algorithm (GA) was used to train the initial connection weights and thresholds of NN. Secondly, the Back Propagation (BP) algorithm was adjusted the final weights and biases. Finally, a numerical example of daily rainfall-runoff data was used to elucidate the forecasting performance of the proposed HGASA-NN model. The HGASA-NN can make use of not only strong global searching ability of the GASA, but also strong local searching ability of the BP algorithm. The forecasting results indicate that the proposed model yields more accurate forecasting results than the BP-NN and pure GA training NN model. Therefore, the HGASA-NN model is a promising alternative for rainfall-runoff forecasting. [ABSTRACT FROM AUTHOR]

Load shedding is some of the essential requirement for maintaining security of modern power systems, particularly in competitive energy markets. This paper proposes an intelligent scheme for fast and accurate load shedding using neural networks for predicting the possible loss of load at the early stage and neuro-fuzzy for determining the amount of load shed in order to avoid a cascading outage. A large scale electrical power system has been considered to validate the performance of the proposed technique in determining the amount of load shed. The proposed techniques can provide tools for improving the reliability and continuity of power supply. This was confirmed by the results obtained in this research of which sample results are given in this paper. [ABSTRACT FROM AUTHOR]

The MMSOM identification method, which had been presented by the authors, is improved to the multiple modeling by the irregular self-organizing map (MMISOM) using the irregular SOM (ISOM). Inputs to the neural networks are parameters of the instantaneous model computed adaptively at every instant. The neural network learns these models. The reference vectors of its output nodes are estimation of the parameters of the local models. At every instant, the model with closest output to the plant output is selected as the model of the plant. ISOM used in this paper is a graph of all the nodes and some of the weighted links between them to make a minimum spanning tree graph. It is shown in this paper that it is possible to add new models if the number of models is initially less than the appropriate one. The MMISOM shows more flexibility to cover the linear model space of the plant when the space is concave. [ABSTRACT FROM AUTHOR]

In this paper, the dynamical behavior of a class of third-order competitive cellular neural networks (CNNs) depending on two parameters, is studied. The class contains a one-parameter family of symmetric CNNs, which are known to be completely stable. The main result is that it is a generic property within the family of symmetric CNNs that complete stability is robust with respect to (small) nonsymmetric perturbations of the neuron interconnections. The paper also gives an exact evaluation of the complete stability margin of each symmetric CNN via the characterization of the whole region in the two-dimensional parameter space where the CNNs turn out to be completely stable. The results are established by means of a new technique to investigate trajectory convergence of the considered class of CNNs in the nonsymmetric case. [ABSTRACT FROM AUTHOR]

Hyper Surface Classification (HSC), which is based on Jordan Curve Theorem in Topology, has proven to be a simple and effective method for classifying a larger database in our previous work. To select a representative subset from the original sample set, the Minimal Consistent Subset (MCS) of HSC is studied in this paper. For HSC method, one of the most important features of MCS is that it has the same classification model as the entire sample dataset, and can totally reflect its classification ability. From this point of view, MCS is the best way of sampling from the original dataset for HSC. Furthermore, because of the minimum property of MCS, every single deletion or multiple deletions from it will lead to a reduction in generalization ability, which can be exactly predicted by the proposed formula in this paper. [ABSTRACT FROM AUTHOR]

Multiple Classifier System (MCS) is a very popular research topic in recent years. It has been proved theoretically and empirically to be better than single classifiers in many scenarios. Creating diverse sets of classifier is one of the key issues in building MCSs. Feature grouping is one of the methods to create diverse classifiers and it has been shown to improve the accuracy of an MCS. In this paper, we propose a new feature grouping method based on Genetic Algorithm (GA) with the localized Generalization Error Model as the evaluation criterion. The combined individual classifiers using the weighted sum are examined in this paper. Moreover, several feature grouping methods are compared with the proposed method in this work. The experimental results on benchmark dataset show that the MCS trained by the proposed method is promising. [ABSTRACT FROM AUTHOR]

This paper presents quantitative measurements/metrics of qualitative entertainment features within computer game environments and proposes artificial intelligence (AI) techniques for optimizing entertainment in such interactive systems. A human-verified metric of interest (i.e. player entertainment in real-time) for predator/prey games and a neuro-evolution on-line learning (i.e. during play) approach have already been reported in the literature to serve this purpose. In this paper, an alternative quantitative approach to entertainment modeling based on psychological studies in the field of computer games is introduced and a comparative study of the two approaches is presented. Feedforward neural networks (NNs) and fuzzy-NNs are used to model player satisfaction (interest) in real-time and investigate quantitatively how the qualitative factors of challenge and curiosity contribute to human entertainment. We demonstrate that appropriate non-extreme levels of challenge and curiosity generate high values of entertainment and we project the extensibility of the approach to other genres of digital entertainment (e.g. mixed-reality interactive playgrounds). [ABSTRACT FROM AUTHOR]

In this paper, the robust synchronization problem is addressed for recurrent neural networks with time-varying delay by linear feedback control. Robustness in the present paper is referred to as the allowance of parameters mismatch between the drive system and the response system. Sufficient conditions for robust synchronization with a synchronization error bound, expressed as linear matrix inequality (LMI), are derived based on Lyapunov–Krasovskii functionals. Both delay-dependent and delay-independent conditions are obtained. Two examples are given to illustrate the results. [ABSTRACT FROM AUTHOR]

This paper focuses on impulsive noise filtering and outliers rejection in gray-scale images. The proposed method combines neural networks, lower-upper-middle (LUM) smoothers and adaptive switching operations to produce a high-quality enhanced image. Extensive experimentation reported in this paper indicates that the proposed method is sufficiently robust, achieves an excellent balance between noise suppression and signal-detail preservation, and outperforms some well-known filters both subjectively and objectively. [ABSTRACT FROM AUTHOR]

Dynamic neural networks with different time-scales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of these networks to be stable. The main contribution of the paper is that Lyapunov function and singularly perturbed technique are combined to access several new stable properties of different time-scales neural networks. Exponential stability and asymptotic stability are obtained by sector and bound conditions. Compared to other papers, these conditions are simpler. Numerical examples are given to demonstrate the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

The study on neural systems is very hot, especially regarding modelling of fuzzy neural networks. The neuron models have been limited in interval [0,1] before. This paper studies the logic operators and neuron models of proposition object based on [a, b]. Any interval [a, b] is called a generalized interval. Firstly, authors provide the conception of proposition object, discussed on the radix space of universal logic. Secondly, using the NTS norms theories, this paper establishes the universal logic operation models on generalized interval [a, b]. Thirdly, the paper builds up a new uniform neuron model of "Not/And/Or/Average" on generalized interval [a, b]. As an instance, authors discuss the neuron models based on standard interval [0,1], which are continuously changeable with generalized correlation coefficient "h" and generalized self-correlation coefficient "k". This work offers important theories and models for neurons reasoning, make it more flexible because of the change of h, k and [a, b], and enlarge its study domain. [ABSTRACT FROM AUTHOR]

In this paper, several simple and new conditions are presented to ensure existence, uniqueness and global exponential robust stability of the equilibrium point of neural networks with delays by using contraction mapping principle, homeomorphism property and Lyapunov method. The conditions given in this paper are easy to verify and apply, and the obtained results improve and extend to those in the literature. In addition, two examples are given to show the effectiveness of the proposed results. [ABSTRACT FROM AUTHOR]

In this paper, we describe a new evolutionary computation approach, called multiphase genetic programming (MPGP). The special features of this approach lie in its variable-granularity representations of chromosomes and their corresponding genetic operations. In the paper, we provide an overview of the MPGP approach as well as details on how the sumo maneuver evolution experiments are carried out and how the MPGP-based case study differs from others. [ABSTRACT FROM AUTHOR]

In spite of rapid evolution of electronic techniques, a number of large-scale applications continue to rely on the use of paper as the dominant medium. This is especially true for processing of bank checks. This paper examines the issue of reading the numerical amount field. In the case of checks, the segmentation of unconstrained strings into individual digits is a challenging task because of connected and overlapping digits, broken digits, and digits that are physically connected to pieces of strokes from neighboring digits. The proposed architecture involves four stages: segmentation of the string into individual digits, normalization, recognition of each character using a neural network classifier, and syntactic verification. Overall, this paper highlights the importance of employing a hybrid architecture that incorporates multiple approaches to provide high recognition rates. [ABSTRACT FROM AUTHOR]

An emulated digital CNN-UM (CASTLE) architecture was published few years ago.1 Different emulated digital CNN-UM architectures are analyzed in the paper. These new modified architectures are optimized according to the silicon area, operating speed or dissipated power. A reconfigurable arithmetic core will also be shown in the paper, by which solution of the neighborhood size can be changed. An advanced CASTLE with pipe-lining is presented. The operation frequency is increased by using this solution in approximately 10 times. [ABSTRACT FROM AUTHOR]

In this paper a new framework for bio-inspired robot locomotion control, entirely based on Cellular Neural Networks (CNNs), is introduced. In fact, CNNs are employed both for generating locomotion patterns in a hexapod robot, and for its trajectory control via visual feedback. In the paper the latter problem will be emphasized, being the CNN locomotion generation problem already treated in literature. Feedback signals are images captured by a camera and processed in real time by a CNN used as analog image processor. The actual framework makes use of a traditional PC where a tool for the synchronization of the visual CNN chip and the robot control has been designed. This paper describes the methodology as an important stage for the study, definition and optimization of the overall control methodology. The results obtained reveal true real time capabilities and the PC interface can be easily substituted with a processing board to be integrated with the visual CNN and with the locomotion-devoted CNN, in order to constitute a unified integrated system for real time visual motion control in complex structures. [ABSTRACT FROM AUTHOR]

Differing from the conventional back-propagation (BP) neural networks, a novel multi-input Euler polynomial neural network, in short, MIEPNN (specifically, 4-input Euler polynomial neural network, 4IEPNN) is established and investigated in this paper. In order to achieve satisfactory performance of the established MIEPNN, a weights and structure determination (WASD) algorithm with pruning-while-growing (PWG) and twice-pruning (TP) techniques is built up for the established MIEPNN. By employing the weights direct determination (WDD) method, the WASD algorithm not only determines the optimal connecting weights between hidden layer and output layer directly, but also obtains the optimal number of hidden-layer neurons. Specifically, a sub-optimal structure is obtained via the PWG technique, then the redundant hidden-layer neurons are further pruned via the TP technique. Consequently, the optimal structure of the MIEPNN is obtained. To provide a reasonable choice in practice, several different MATLAB computing routines related to the WDD method are studied. Comparative numerical-experiment results of the 4IEPNN using these different MATLAB computing routines and the standard multi-layer perceptron (MLP) neural network further verify the superior performance and efficacy of the proposed MIEPNN equipped with the WASD algorithm including PWG and TP techniques in terms of training, testing and predicting. [ABSTRACT FROM AUTHOR]

Most current speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. In these systems acoustic inputs are represented by Mel Frequency Cepstral Coefficients temporal spectrogram known as frames. But MFCC is not robust to noise. Consequently, with different train and test conditions the accuracy of speech recognition systems decreases. On the other hand, using MFCCs of larger window of frames in GMMs needs more computational power. In this paper, Deep Belief Networks (DBNs) are used to extract discriminative information from larger window of frames. Nonlinear transformations lead to high-order and low-dimensional features which are robust to variation of input speech. Multiple speaker isolated word recognition tasks with 100 and 200 words in clean and noisy environments has been used to test this method. The experimental results indicate that this new method of feature encoding result in much better word recognition accuracy. [ABSTRACT FROM AUTHOR]

This paper investigates the capabilities of radial basis function networks (RBFN) and kernel neural networks (KNN), i.e. a specific probabilistic neural networks (PNN), and studies their similarities and differences. In order to avoid the huge amount of hidden units of the KNNs (or PNNs) and reduce the training time for the RBFNs, this paper proposes a new feedforward neural network model referred to as radial basis probabilistic neural network (RBPNN). This new network model inherits the merits of the two old odels to a great extent, and avoids their defects in some ways. Finally, we apply this new RBPNN to the recognition of one-dimensional cross-images of radar targets (five kinds of aircrafts), and the experimental results are given and discussed. [ABSTRACT FROM AUTHOR]

A fundamental question in the field of artificial neural networks is what set of problems a given class of networks can perform (computability). Such a problem can be made less general, but no less important, by asking what these networks could learn by using a given training procedure (learnability). The basic purpose of this paper is to address the learnability problem. Specifically, it analyses the learnability of sequential RAM-based neural networks. The analytical tools used are those of Automata Theory. In this context, this paper establishes which class of problems and under what conditions such networks, together with their existing learning rules, can learn and generalise. This analysis also yields techniques for both extracting knowledge from and inserting knowledge into the networks. The results presented here, besides helping in a better understanding of the temporal behaviour of sequential RAM-based networks, could also provide useful insights for the integration of the symbolic/connectionist paradigms. [ABSTRACT FROM AUTHOR]

One of the most difficult problems in cluster analysis is the identification of the number of groups in a dataset especially in the presence of missing value. Since traditional clustering methods assumed the real number of clusters to be known. However, in real world applications the number of clusters is generally not known a priori. Also, most of clustering methods were developed to analyse complete datasets, they cannot be applied to many practical problems, e.g., on incomplete data. This paper focuses, first, on an algorithm of a fuzzy clustering approach, called OCS-FSOM. The proposed algorithm is based on neural network and uses Optimal Completion Strategy for missing value estimation in incomplete dataset. Then, we propose an extension of our algorithm, to tackle the problem of estimating the number of clusters, by using a multi level OCS-FSOM method. The new algorithm called Multi-OCSFSOM is able to find the optimal number of clusters by using a statistical criterion, that aims at measuring the quality of obtained partitions. Carried out experiments on real-life datasets highlights a very encouraging results in terms of exact determination of optimal number of clusters. [ABSTRACT FROM AUTHOR]

In this paper, a hierarchical structure based convolutional neural network is proposed to provide the ability for robust information processing. The weight sharing ability of convolutional neural networks (CNNs) is considered as a level of hierarchy in these networks. Weight sharing reduces the number of free parameters and improves the generalization ability. In the proposed structure, a small CNN which is used for feature extractor is shared between the whole input image pixels. A scalable architecture for implementing extensive CNNs is resulted using a smaller and modularized trainable network to solve a large and complicated task. The proposed structure causes less training time, fewer numbers of parameters and higher test data accuracy. The recognition accuracy for recognizing unseen data shows improvement in generalization. Also presented are application examples for face recognition. The comprehensive experiments completed on ORL, Yale and JAFFE face databases show improved classification rates and reduced training time and network parameters. [ABSTRACT FROM AUTHOR]

Nucleus segmentation is one of important steps in the automatic white blood cell differential counting. In this paper, we proposed a technique to segment images of the nucleus. We analyze a set of white-blood-cell-nucleus-based features using color fuzzy texture spectrum (Base 5). We applied artificial neural network for classification. We compared the results with moment based features. The classification performances are evaluated by class wise classification rates. The results show that the features using nucleus alone could be utilized to achieve a classification rate of 99.05% on the test sets. [ABSTRACT FROM AUTHOR]

In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR) are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual single point prediction approach could result into curves that are inconsistent, exhibiting scattered behavior as compared to the real curves. Support Vector Regressors and Functional Networks are explored in this paper to solve this problem. Inputs into the developed models include hydrocarbon and non-hydrocarbon crude oil compositions and other strongly correlating reservoir parameters. Graphical plots and statistical error measures, including root mean square error and average absolute percent relative error, have been used to evaluate the performance of the models. A comparative study is performed between the two techniques and with the conventional feed forward artificial neural networks. Most importantly, the predicted curves are consistent with the shapes of the physical curves of the mentioned oil properties, preserving the need of such curves for interpolation and ensuring conformity of the predicted curves with the conventional properties. [ABSTRACT FROM AUTHOR]

In this paper, novel virtual instrumentation based systems for real-time collision-free path planning and tracking control of mobile robots are proposed. The developed virtual instruments are computationally simple and efficient in comparison to other approaches, which act as a new soft-computing platform to implement a biologically-inspired neural network. This neural network is topologically arranged with only local lateral connections among neurons. The dynamics of each neuron is described by a shunting equation with both excitatory and inhibitory connections. The neural network requires no off-line training or on-line learning, which is capable of planning a comfortable trajectory to the target without suffering from neither the too close nor the too far problems. LabVIEW is chosen as the software platform to build the proposed virtual instrumentation systems, as it is one of the most important industrial platforms. We take the initiative to develop the first neuro-dynamic application in LabVIEW. The developed virtual instruments could be easily used as educational and research tools for studying various robot path planning and tracking situations that could be easily understood and analyzed step by step. The effectiveness and efficiency of the developed virtual instruments are demonstrated through simulation and comparison studies. [ABSTRACT FROM AUTHOR]

To improve the modeling performance - such as accuracy and robustness - of artificial neural network (ANN), a new combined ANN and corresponding optimal modeling method are proposed in this paper. The combined ANN consists of two parallel sub-networks, and methods such as "early stopping" and "data resampling" are jointly used in training process to reduce the sensitivity of the modeling performance to its structure. To achieve better performance, the structure of combined ANN is proposed to be adjusted dynamically according to the information of expectation error and real error. Simulation experimental results verify that the optimal modeling method using combined ANN can achieve much better performance than the traditional method. [ABSTRACT FROM AUTHOR]

Building agents that negotiate on behalf of their owners aiming to maximise their utility is a quite challenging research field in the artificial intelligence domain. In this paper, such agents are enhanced with techniques based on neural networks (NNs) to predict their opponents' negotiation behaviour, thus achieving more profitable results and better resource utilization. The NNs are used to early detect the cases where agreements are not achievable, supporting the decision of the agents to withdraw or not from the negotiation threads. The designed NN-assisted negotiation strategies have been evaluated via extensive experiments and are proven to be very useful. [ABSTRACT FROM AUTHOR]

In this paper, an improved web page classification method (IWPCM) using neural networks to identify the illicit contents of web pages is proposed. The proposed IWPCM approach is based on the improvement of feature selection of the web pages using class based feature vectors (CPBF). The CPBF feature selection approach has been calculated by considering the important term's weight for illicit web documents and reduce the dependency of the less important term's weight for normal web documents. The IWPCM approach has been examined using the modified term-weighting scheme by comparing it with several traditional term-weighting schemes for non-illicit and illicit web contents available from the web. The precision, recall, and F1 measures have been used to evaluate the effectiveness of the proposed IWPCM approach. The experimental results have shown that the proposed improved term-weighting scheme has been able to identify the non-illicit and illicit web contents available from the experimental datasets. [ABSTRACT FROM AUTHOR]

The development of satellite image acquisition tools helped improving the extraction of information about natural scenes. In the proposed approach, we try to minimize imperfections accompanying the image interpretation process and to maximize useful information extracted from these images through the use of blind source separation (BSS) and fusion methods. In order to extract maximum information from multi-sensor images, we propose to use three algorithms of BSS that are FAST- ICA2D, JADE2D, and SOBI2D. Then by employing various fusion methods such as the probability, possibility, and evidence methods we can minimize both imprecision and uncertainty. In this paper, we propose a hybrid approach based on five main steps. The first step is to apply the three BSS algorithms to the satellites images; it results in obtaining a set of image sources representing each a facet of the land cover. A second step is to choose the image having the maximum of kurtosis and negentropy. After the BSS evaluation, we proceed to the training step using neural networks. The goal of this step is to provide learning regions which are useful for the fusion step. The next step consists in choosing the best adapted fusion method for the selected source images through a case-based reasoning (CBR) module. If the CBR module does not contain a case similar to the one we are seeking, we proceed to apply the three fusion methods. The evaluation of fusion methods is a necessary step for the learning process of our CBR. [ABSTRACT FROM AUTHOR]

In this paper, we consider a class of fuzzy BAM neural networks with distributed delays and variable coefficients. By using Brouwer fixed point theorem and differential inequality, we obtain some sufficient conditions for the existence and global exponential stability of periodic solutions for a class of fuzzy BAM neural networks with distributed delays and variable coefficients. In addition, we also present an illustrative example to show the effectiveness of obtained results. [ABSTRACT FROM AUTHOR]

Cascade process, such as wastewater treatment plant, includes many nonlinear sub-systems and many variables. When the number of sub-systems is big, the input-output relation in the first block and the last block cannot represent the whole process. In this paper we use two techniques to overcome the above problem. Firstly we propose a new neural model: hierarchical neural networks to identify the cascade process; then we use serial structural mechanism model based on the physical equations to connect with neural model. A stable learning algorithm and theoretical analysis are given. Finally, this method is used to model a wastewater treatment plant. Real operational data of wastewater treatment plant is applied to illustrate the modeling approach. [ABSTRACT FROM AUTHOR]

This paper focusses on a novel discrete-time reduced order neural observer for nonlinear systems, which model is assumed to be unknown. This neural observer is robust in presence of external and internal uncertainties. The proposed scheme is based on a discrete-time recurrent high order neural network (RHONN) trained with an extended Kalman filter (EKF)-based algorithm, using a parallel configuration. This work includes the stability proof of the estimation error on the basis of the Lyapunov approach; to illustrate the applicability, simulation results for a nonlinear oscillator are included. [ABSTRACT FROM AUTHOR]

In this paper, a recurrent high order neural observer (RHONO) for anaerobic processes is proposed. The main objective is to estimate variables of methanogenesis: biomass, substrate and inorganic carbon in a completely stirred tank reactor (CSTR). The recurrent high order neural network (RHONN) structure is based on the hyperbolic tangent as activation function. The learning algorithm is based on an extended Kalman filter (EKF). The applicability of the proposed scheme is illustrated via simulation. A validation using real data from a lab scale process is included. Thus, this observer can be successfully implemented for control purposes. [ABSTRACT FROM AUTHOR]

This paper presents a repair algorithm for the design of a Radial Basis Function (RBF) neural network. The proposed repair RBF (RRBF) algorithm starts from a single prototype randomly initialized in the feature space. The algorithm has two main phases: an architecture learning phase and a parameter adjustment phase. The architecture learning phase uses a repair strategy based on a sensitivity analysis (SA) of the network's output to judge when and where hidden nodes should be added to the network. New nodes are added to repair the architecture when the prototype does not meet the requirements. The parameter adjustment phase uses an adjustment strategy where the capabilities of the network are improved by modifying all the weights. The algorithm is applied to two application areas: approximating a non-linear function, and modeling the key parameter, chemical oxygen demand (COD) used in the waste water treatment process. The results of simulation show that the algorithm provides an efficient solution to both problems. [ABSTRACT FROM AUTHOR]

Neural networks (NNs) provide an efficient tool that can be trained to estimate the value of output parameters given certain metrics. In this paper, NNs are used to enhance intelligent agents that negotiate on behalf of their owners aiming to maximize their utility. More specifically, NNs are exploited in order to predict the hybrid negotiation behavior of the agents' opponents, thus achieving more profitable results for the parties these agents represent. The NNs provide the means so that the agents can early detect the cases where agreements are not achievable, thus supporting their decision to withdraw or not from the negotiation threads. The designed NN-assisted negotiation strategies have been evaluated via extensive experiments and are proven to be very useful, as they manage to significantly reduce the average duration of the negotiation threads. [ABSTRACT FROM AUTHOR]