Search

Traffic data are the information source for traffic control and management. With the development and integration of Intelligent Transportation Systems, many applications and their respective sensors and detectors are a rich source of data about transportation system characteristics and performance. However, because of the limitation of databases and devices, the huge amounts of traffic data can not be stored without reduction. In this paper, an approach for urban traffic volume compression based on artificial neural network is proposed. The lossy compression of data is realized by using a set of three-layer back-propagation neural networks to remove the correlation within traffic volumes. The model has both a small reproduction error and a relatively high compression ratio.

The structure and function of retinal vessels play a crucial role in diagnosing and treating various ocular and systemic diseases. Therefore, the accurate segmentation of retinal vessels is of paramount importance to assist a clinical diagnosis. U-Net has been highly praised for its outstanding performance in the field of medical image segmentation. However, with the increase in network depth, multiple pooling operations may lead to the problem of crucial information loss. Additionally, handling the insufficient processing of local context features caused by skip connections can affect the accurate segmentation of retinal vessels. To address these problems, we proposed a novel model for retinal vessel segmentation. The proposed model is implemented based on the U-Net architecture, with the addition of two blocks, namely, an MsFE block and MsAF block, between the encoder and decoder at each layer of the U-Net backbone. The MsFE block extracts low-level features from different scales, while the MsAF block performs feature fusion across various scales. Finally, the output of the MsAF block replaces the skip connection in the U-Net backbone. Experimental evaluations on the DRIVE dataset, CHASE_DB1 dataset, and STARE dataset demonstrated that MsAF-UNet exhibited excellent segmentation performance compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Radiation therapy relies on quality assurance (QA) to verify dose delivery accuracy. However, current QA methods suffer from operation lag as well as inaccurate performance. Hence, to address these shortcomings, this paper proposes a QA neural network model based on branch architecture, which is based on the analysis of the category features of the QA complexity metrics. The designed branch network focuses on category features, which effectively improves the feature extraction capability for complexity metrics. The branch features extracted by the model are fused to predict the GPR for more accurate QA. The performance of the proposed method was validated on the collected dataset. The experiments show that the prediction performance of the model outperforms other QA methods; the average prediction errors for the test set are 2.12% (2%/2 mm), 1.69% (3%/2 mm), and 1.30% (3%/3 mm). Moreover, the results indicate that two-thirds of the validation samples' model predictions perform better than the clinical evaluation results, suggesting that the proposed model can assist physicists in the clinic. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a prevalent eye disease that poses a potential risk of blindness. Nevertheless, due to the small size of diabetic retinopathy lesions and the high interclass similarity in terms of location, color, and shape among different lesions, the segmentation task is highly challenging. To address these issues, we proposed a novel framework named nmODE-Unet, which is based on the nmODE (neural memory Ordinary Differential Equation) block and U-net backbone. In nmODE-Unet, the shallow features serve as input to the nmODE block, and the output of the nmODE block is fused with the corresponding deep features. Extensive experiments were conducted on the IDRiD dataset, e_ophtha dataset, and the LGG segmentation dataset, and the results demonstrate that, in comparison to other competing models, nmODE-Unet showcases a superior performance. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have emerged as a prominent model in medical image segmentation, achieving remarkable advancements in clinical practice. Despite the promising results reported in the literature, the effectiveness of DNNs necessitates substantial quantities of high-quality annotated training data. During experiments, we observe a significant decline in the performance of DNNs on the test set when there exists disruption in the labels of the training dataset, revealing inherent limitations in the robustness of DNNs. In this paper, we find that the neural memory ordinary differential equation (nmODE), a recently proposed model based on ordinary differential equations (ODEs), not only addresses the robustness limitation but also enhances performance when trained by the clean training dataset. However, it is acknowledged that the ODE-based model tends to be less computationally efficient compared to the conventional discrete models due to the multiple function evaluations required by the ODE solver. Recognizing the efficiency limitation of the ODE-based model, we propose a novel approach called the nmODE-based knowledge distillation (nmODE-KD). The proposed method aims to transfer knowledge from the continuous nmODE to a discrete layer, simultaneously enhancing the model's robustness and efficiency. The core concept of nmODE-KD revolves around enforcing the discrete layer to mimic the continuous nmODE by minimizing the KL divergence between them. Experimental results on 18 organs-at-risk segmentation tasks demonstrate that nmODE-KD exhibits improved robustness compared to ODE-based models while also mitigating the efficiency limitation. [ABSTRACT FROM AUTHOR]

Nowadays, industrial control system (ICS) has begun to integrate with the Internet. While the Internet has brought convenience to ICS, it has also brought severe security concerns. Traditional ICS network traffic anomaly detection methods rely on statistical features manually extracted using the experience of network security experts. They are not aimed at the original network data, nor can they capture the potential characteristics of network packets. Therefore, the following improvements were made in this study: (1) A dataset that can be used to evaluate anomaly detection algorithms is produced, which provides raw network data. (2) A request response-based convolutional neural network named RRCNN is proposed, which can be used for anomaly detection of ICS network traffic. Instead of using statistical features manually extracted by security experts, this method uses the byte sequences of the original network packets directly, which can extract potential features of the network packets in greater depth. It regards the request packet and response packet in a session as a Request-Response Pair (RRP). The feature of RRP is extracted using a one-dimensional convolutional neural network, and then the RRP is judged to be normal or abnormal based on the extracted feature. Experimental results demonstrate that this model is better than several other machine learning and neural network models, with F1, accuracy, precision, and recall above 99%. [ABSTRACT FROM AUTHOR]

Medical images contain complex information, and the automated analysis of medical images can greatly assist doctors in clinical decision making. Therefore, the automatic segmentation of medical images has become a hot research topic in recent years. In this study, a novel architecture called a contoured convolutional transformer (CCTrans) network is proposed to solve the segmentation problem. A dual convolutional transformer block and a contoured detection module are designed, which integrate local and global contexts to establish reliable relational connections. Multi-scale features are effectively utilized to enhance semantic feature understanding. The dice similarity coefficient (DSC) is employed to evaluate experimental performance. Two public datasets with two different modalities are chosen as the experimental datasets. Our proposed method achieved an average DSC of 83.97% on a synapse dataset (abdominal multi-organ CT) and 92.15% on an ACDC dataset (cardiac MRI). Especially for the segmentation of small and complex organs, our proposed model achieves better segmentation results than other advanced approaches. Our experiments demonstrate the effectiveness and robustness of the novel method and its potential for real-world applications. The proposed CCTrans network offers a universal solution with which to achieve precise medical image segmentation. [ABSTRACT FROM AUTHOR]

Question answering systems have become prominent in all areas, while in the medical domain it has been challenging because of the abundant domain knowledge. Retrieval based approach has become promising as large pretrained language models come forth. This study focuses on building a retrieval‐based medical question answering system, tackling the challenge with large language models and knowledge extensions via graphs. We first retrieve an extensive but coarse set of answers via Elasticsearch efficiently. Then, we utilize semantic matching with pretrained language models to achieve a fine‐grained ranking enhanced with named entity recognition and knowledge graphs to exploit the relation of the entities in question and answer. A new architecture based on siamese structures for answer selection is proposed. To evaluate the approach, we train and test the model on two Chinese data sets, NLPCC2017 and cMedQA. We also conduct experiments on two English data sets, TREC‐QA and WikiQA. Our model achieves consistent improvement as compared to strong baselines on all data sets. Qualification studies with cMedQA and our in‐house data set show that our system gains highly competitive performance. The proposed medical question answering system outperforms baseline models and systems in quantification and qualification evaluations. [ABSTRACT FROM AUTHOR]

Ultrasound imaging is one of the most frequently used diagnostic tools for detecting and analyzing abnormalities of the breast. Recently proposed methods for the automated analysis of breast ultrasound images have shown great success, especially in the classification of breast abnormalities into malignant or benign lesions. In this study, we explore the use of a deep convolutional neural network with a multi-scale module for the automated assessment of BI-RADS category on breast ultrasound images. We propose a multi-input region of interest extraction method to extract the breast region from ultrasound images, with this method avoiding the deformation of region of interest images and providing high classification performance. Moreover, we also propose an order-constrained loss function that fully considers the continuity between BI-RADS categories and shows higher performance than traditional loss functions. A large annotated dataset containing 8246 breast ultrasound images was collected to train and evaluate the proposed methods. Ablation experiments were performed to validate the effectiveness of the proposed methods. Experimental results indicate that our method can be used to mimic experienced radiologists in the assessment of the BI-RADS category of breast ultrasound images and that the automated interpretations could be acceptable in routine clinical breast ultrasound examination reports. [ABSTRACT FROM AUTHOR]

Dropout is an important training method for deep neural networks, because it can help avoid over-fitting. Traditional dropout methods and many extended dropout methods, omit some of the neurons' activation values according to the probabilities. These methods calculate the activation probability of neurons using the designed formula, without providing a plausible explanation of the calculation method. This paper proposes an adaptive sparse dropout (AS-Dropout) method for neural network training. The algorithm maps the neurons' activation values in a layer to a relative linear range of a sigmoid function, determines the ratio of active neurons by a probability calculation process, and drops most of neurons according to the probabilities. The probability calculation depends on the activation values of the neurons. The selection of active neurons is according to the probabilities. Therefore, AS-Dropout learns both the certainty and uncertainty in deep neural networks. Additionally, since only a small number of neurons are active, AS-Dropout increases the sparsity of the network. We applied AS-Dropout in different neural network structures. When evaluated on MNIST, COIL-100, and Caltech-101 datasets, the experimental results demonstrated that, overall, AS-Dropout substantially outperformed the traditional dropout and some improved dropout methods. [ABSTRACT FROM AUTHOR]

Lung cancer is one of the most common and fatal types of cancer, and pulmonary nodule detection plays a crucial role in the screening and diagnosis of this disease. A well-trained deep neural network model can help doctors to find nodules on computed tomography(CT) images while requiring lots of labeled data. However, currently available annotating systems are not suitable for annotating pulmonary nodules in CT images. We propose a web-based lung nodules annotating system named as DeepLNAnno. DeepLNAnno has a unique three-tier working process and loads of features like semi-automatic annotation, which not only make it much easier for doctors to annotate compared to some other annotating systems but also increase the accuracy of the labels. We invited a medical group from West China Hospital to annotate the CT images using our DeepLNAnno system, and collected a large number of labeled data. The results of our experiments demonstrated that a usable nodule-detection system is developed, and good benchmark scores on our evaluation data are obtained. [ABSTRACT FROM AUTHOR]

Audio classification is regarded as a great challenge in pattern recognition. Although audio classification tasks are always treated as independent tasks, tasks are essentially related to each other such as speakers' accent and speakers' identification. In this paper, we propose a Deep Neural Network (DNN)-based multi-task model that exploits such relationships and deals with multiple audio classification tasks simultaneously. We term our model as the gated Residual Networks (GResNets) model since it integrates Deep Residual Networks (ResNets) with a gate mechanism, which extract better representations between tasks compared with Convolutional Neural Networks (CNNs). Specifically, two multiplied convolutional layers are used to replace two feed-forward convolution layers in the ResNets. We tested our model on multiple audio classification tasks and found that our multi-task model achieves higher accuracy than task-specific models which train the models separately. [ABSTRACT FROM AUTHOR]

Deep learning (DL) aims at learning the meaningful representations. A meaningful representation gives rise to significant performance improvement of associated machine learning (ML) tasks by replacing the raw data as the input. However, optimal architecture design and model parameter estimation in DL algorithms are widely considered to be intractable. Evolutionary algorithms are much preferable for complex and nonconvex problems due to its inherent characteristics of gradient-free and insensitivity to the local optimal. In this paper, we propose a computationally economical algorithm for evolving unsupervised deep neural networks to efficiently learn meaningful representations, which is very suitable in the current big data era where sufficient labeled data for training is often expensive to acquire. In the proposed algorithm, finding an appropriate architecture and the initialized parameter values for an ML task at hand is modeled by one computational efficient gene encoding approach, which is employed to effectively model the task with a large number of parameters. In addition, a local search strategy is incorporated to facilitate the exploitation search for further improving the performance. Furthermore, a small proportion labeled data is utilized during evolution search to guarantee the learned representations to be meaningful. The performance of the proposed algorithm has been thoroughly investigated over classification tasks. Specifically, error classification rate on MNIST with 1.15% is reached by the proposed algorithm consistently, which is considered a very promising result against state-of-the-art unsupervised DL algorithms. [ABSTRACT FROM AUTHOR]

Object tracking still remains challenging in computer vision because of the severe object variation, e.g., deformation, occlusion, and rotation. To handle the object variation and achieve robust object tracking performance, we propose a novel relationship-based tracking algorithm using neural networks in this paper. Compared with existing approaches in the literature, our method assumes the targeted object to be consisted of several parts and considers the evolution of the topology structure among these parts. After training a candidate neural network for predicting the probable areas each part may locate at in the successive frame, we then design a novel collaboration neural network to determine the precise area each part will locate at with account for the topology structure among these individual parts, which is learned from their historical physical locations during online tracking process. Experimental results show that the proposed method outperforms state-of-the-art trackers on a benchmark dataset, yielding the significant improvements in accuracy on high-distorted sequences. [ABSTRACT FROM AUTHOR]

With continuing commercialization of remote sensing satellites, the high resolution remote sensing image has been increasingly used in various fields of our life. However, processing technology of high resolution remote sensing images is still a tough problem. How to extract useful information from the massive information in high resolution remote sensing images is significant to the subsequent process. A multi-phase oil tank recognition of remote sensing images, namely coarse detection and artificial neural network (ANN) recognition, is proposed. The experimental results of algorithms presented in this paper show that the proposed processing technology is reliable and effective. [ABSTRACT FROM AUTHOR]

Connections play a crucial role in neural network (NN) learning because they determine how information flows in NNs. Suitable connection mechanisms may extensively enlarge the learning capability and reduce the negative effect of gradient problems. In this paper, a new delay connection is proposed for Long Short-Term Memory (LSTM) unit to develop a more sophisticated recurrent unit, called Delay Connected LSTM (DCLSTM). The proposed delay connection brings two main merits to DCLSTM with introducing no extra parameters. First, it allows the output of the DCLSTM unit to maintain LSTM, which is absent in the LSTM unit. Second, the proposed delay connection helps to bridge the error signals to previous time steps and allows it to be back-propagated across several layers without vanishing too quickly. To evaluate the performance of the proposed delay connections, the DCLSTM model with and without peephole connections was compared with four state-of-the-art recurrent model on two sequence classification tasks. DCLSTM model outperformed the other models with higher accuracy and F1_score. Furthermore, the networks with multiple stacked DCLSTM layers and the standard LSTM layer were evaluated on Penn Treebank (PTB) language modeling. The DCLSTM model achieved lower perplexity (PPL)/bit-per-character (BPC) than the standard LSTM model. The experiments demonstrate that the learning of the DCLSTM models is more stable and efficient. [ABSTRACT FROM AUTHOR]

With the rapid development of automation technology, self-adaptive control methods have been widely used for drum shearers for the rapid development of automation technology. The main objective of this paper is to propose a control system wherein the motion parameters can be adjusted adaptively with the variation in the cutting resistance. The cutting resistance recognition is achieved by using the theory of wavelet packet decomposition and back propagation neural network. The motion parameters comprising hauling and drum rotation speeds are optimized by using particle swarm optimization algorithm. Different speed-control strategies are proposed to meet the variations of the cutting resistance. A selfadaptive control system model is developed to realize the self-adaptive control of the drum shearer. Finally, a simulation test is conducted to validate the effectiveness of the cutting resistance recognition method. The speed-control strategies are validated through an experimental bench test. [ABSTRACT FROM AUTHOR]

In this paper, we illustrate how to learn a general straightforward similarity function from raw image pairs, which is a fundamental task in computer vision. To encode the function, inspired by the recent achievements of deep learning methods, we explore several deep neural networks and adopt one of the suitable networks to our task encoding implementation with several models on benchmark datasets UKBench and Holidays. The adopted network achieves comparable overall results and especially presents the excellent learning ability for global-similar data. Compared to previous approaches, this function eliminates the complex handcrafted features extraction, and utilizes pairwise correlation information by the jointly processing. [ABSTRACT FROM AUTHOR]

Moving object recognition (MOR) is an important but challenging problem in the field of computer vision. The aim of MOR is to recognize moving objects in a given video dataset. Convolutional neural networks (CNNs) have been extensively used for image recognition and video analysis problems. Recently, a 3D-CNN, which contains 3D convolution layers, was proposed to address MOR problems by successfully extracting spatiotemporal features. In this paper, a multi-view (MV) 3D-CNN is proposed for MOR. This model combines 3D-CNNs with a well-known MV learning technique. Because multi-view learning techniques have the ability to obtain more view-related features from videos captured by different cameras, the proposed model can extract more representative features. Moreover, the model contains a special view-pooling layer that can fuse the feature information from previous layers. The proposed MV3D-CNN is applied to both real-world moving vehicle recognition and sign language recognition tasks. The experimental results show that the proposed model possesses good performance. [ABSTRACT FROM AUTHOR]

This paper presents a state-of-the-art application of fractional hopfield neural networks (FHNNs) to defend against chip cloning attacks, and provides insight into the reason that the proposed method is superior to physically unclonable functions (PUFs). In the past decade, PUFs have been evolving as one of the best types of hardware security. However, the development of the PUFs has been somewhat limited by its implementation cost, its temperature variation effect, its electromagnetic interference effect, the amount of entropy in it, etc. Therefore, it is imperative to discover, through promising mathematical methods and physical modules, some novel mechanisms to overcome the aforementioned weaknesses of the PUFs. Motivated by this need, in this paper, we propose applying the FHNNs to defend against chip cloning attacks. At first, we implement the arbitrary-order fractor of a FHNN. Secondly, we describe the implementation cost of the FHNNs. Thirdly, we propose the achievement of the constant-order performance of a FHNN when ambient temperature varies. Fourthly, we analyze the electrical performance stability of the FHNNs under electromagnetic disturbance conditions. Fifthly, we study the amount of entropy of the FHNNs. Lastly, we perform experiments to analyze the pass-band width of the fractor of an arbitrary-order FHNN and the defense against chip cloning attacks capability of the FHNNs. In particular, the capabilities of defense against chip cloning attacks, anti-electromagnetic interference, and anti-temperature variation of a FHNN are illustrated experimentally in detail. Some significant advantages of the FHNNs are that their implementation cost is considerably lower than that of the PUFs, their electrical performance is much more stable than that of the PUFs under different temperature conditions, their electrical performance stability of the FHNNs under electromagnetic disturbance conditions is much more robust than that of the PUFs, and their amount of entropy is significantly higher than that of the PUFs with the same rank circuit scale. [ABSTRACT FROM AUTHOR]

The auto-encoder model plays a crucial role in the success of deep learning. During the pre-training phase, auto-encoders learn a representation that helps improve the performance of the entire neural network during the fine-tuning phase of deep learning. However, the learned representation is not always meaningful and the network does not necessarily achieve higher performance with such representation because auto-encoders are trained in an unsupervised manner without knowing the specific task targeted in the fine-tuning phase. In this paper, we propose a novel approach to train auto-encoders by adding an explicit guiding term to the traditional reconstruction cost function that encourages the auto-encoder to learn meaningful features. Particularly, the guiding term is the classification error with respect to the representation learned by the auto-encoder, and a meaningful representation means that a network using the representation as input has a low classification error in a classification task. In our experiments, we show that the additional explicit guiding term helps the auto-encoder understand the prospective target in advance. During learning, it can drive the learning toward a minimum with better generalization with respect to the particular supervised task on the dataset. Over a range of image classification benchmarks, we achieve equal or superior results to baseline auto-encoders with the same configuration. [ABSTRACT FROM AUTHOR]

Auto-encoders play a fundamental role in unsupervised feature learning and learning initial parameters of deep architectures for supervised tasks. For given input samples, robust features are used to generate robust representations from two perspectives: (1) invariant to small variation of samples and (2) reconstruction by decoders with minimal error. Traditional auto-encoders with different regularization terms have symmetrical numbers of encoder and decoder layers, and sometimes parameters. We investigate the relation between the number of layers and propose an unsymmetrical structure, i.e., an unsymmetrical auto-encoder (UAE), to learn more effective features. We present empirical results of feature learning using the UAE and state-of-the-art auto-encoders for classification tasks with a range of datasets. We also analyze the gradient vanishing problem mathematically and provide suggestions for the appropriate number of layers to use in UAEs with a logistic activation function. In our experiments, UAEs demonstrated superior performance with the same configuration compared to other auto-encoders. [ABSTRACT FROM AUTHOR]

In this paper, the problem that we are interested is constructing $$l_{1}$$ -graphs for subspace learning via recurrent neural networks. We propose a closed affine subspace learning (CASL) method to do so. The problem of CASL is formulated as an optimization problem described by an energy function in the non-negative orthant. The sufficient conditions for keeping the minimum points of the energy function in the non-negative orthant are given. A model of Lotka-Volterra recurrent neural networks is constructed to solve the optimization problem in terms of these sufficient conditions. It shows that the set of stable attractors of the network model just equals the set of minimum points of the energy function in the non-negative orthant. Based on these equivalences, the problem of CASL can be solved by running the proposed LV RNNs to obtain the stable attractors. The $$l_{1}$$ -graphs then can be constructed. Experiments on some synthetic and real data show that the $$l_{1}$$ -graphs constructed in this way are more effective, especially when processing the data sampled from multiple manifolds. [ABSTRACT FROM AUTHOR]

A candidate set of support vectors is selected by using pulse-coupled neural networks to reduce computational cost in learning phase for support vector machines (SVMs). The size of the candidate set of support vectors selected this way is smaller than that of the original training samples so that the computation complexity in learning process for support vectors machines based on this candidate set is reduced and the learning process is accelerated. On the other hand, the candidate set of support vectors includes almost all support vectors, and the performance of the SVM based on this candidate set matches the performance when the full training samples are used. [ABSTRACT FROM AUTHOR]

Abstract: Shortest path tree (SPT) computation is a critical issue in many real world problems, such as routing in networks. It is also a constrained optimization problem, which has been studied by many authors in recent years. Typically, it is solved by heuristic algorithms, such as the famous Dijkstra''s algorithm, which can quickly provide a good solution in most instances. However, with the scale of problem increasing, these methods are inefficient and may consume a considerable amount of CPU time. Neural networks, which are massively parallel models, can solve this question easily. This paper presents an efficient modified continued pulse coupled neural network (MCPCNN) model for SPT computation in a large scale instance. The proposed model is topologically organized with only local lateral connections among neurons. The start neuron fires first, and then the firing event spreads out through the lateral connections among the neurons, like the propagation of a wave. Each neuron records its parent, that is, the neighbor which caused it to fire. It proves that the generated wave in the network spreads outward with travel times proportional to the connection weight between neurons. Thus, the generated path is always the global optimal shortest path from the source to all destinations. The proposed model is also applied to generate SPTs for a real given graph step by step. The effectiveness and efficiency of the proposed approach is demonstrated through simulation and comparison studies. [Copyright &y& Elsevier]

Abstract: A class of simplified background neural networks model with a large number of neurons is proposed. Continuous attractors of the simplified model are studied in this paper. It contains: (1) When the background inputs are set to zero and the excitatory connections are in Gaussian shape, continuous attractors of the new network are obtained under some condition. (2) When the background inputs are nonzero and the excitatory connections are still in Gaussian shape, continuous attractors are achieved under some appropriately selected condition. (3) Discussions and examples are used to illustrate the theories developed. [Copyright &y& Elsevier]

Abstract: Motivated by Salinas''s (2003) original discovery in and inspired by Oja''s (1982) seminal work in , in this paper, we propose a class of simplified background neural networks model with two subnetworks. Some basic dynamic properties including boundedness, global attractivity, stability, and complete convergence are analyzed rigorously. The main contributions in this paper are as follows: (1) The boundedness of the new model is verified and conditions for global attractivity are derived. (2) Conditions on asymptotically stable of equilibrium points are obtained. (3) Complete convergence for the new network is proved by constructing a novel energy function. Finally, numerical examples demonstrate our theoretical results. [Copyright &y& Elsevier]

The concepts of selectable and unselectable sets are proposed to describe some interesting dynamical properties of a class of recurrent neural networks (RNNs) with saturated piecewise linear transfer function. A set of neurons is said to be selectable if it can be co-unsaturated at a stable equilibrium point by some external input. A set of neurons is said to be unselectable if it is not selectable, i.e., such set of neurons can never be co-unsaturated at any stable equilibrium point regardless of what the input is. The importance of such concepts is that they enable a new perspective of the memory in RNNs. Necessary and sufficient conditions for the existence of selectable and unselectable sets of neurons are obtained. As an application, the problem of group selection is discussed by using such concepts. It shows that, under some conditions, each group is a selectable set, and each selectable set is contained in some group. Thus, groups are indicated by selectable sets of the RNNs and can be selected by external inputs. Simulations are carried out to further illustrate the theory. [ABSTRACT FROM AUTHOR]

Ten notched I-beams of A572-G50 bridge steel were loaded in three-point bending, and back-propagation neural network (BPNN) fatigue life predictions were performed on the acoustic emission (AE) amplitude histogram data taken during fatigue cycling. BPNN fatigue life predictions based on the AE data from the first (0-25%), second (25-50%), and third (50-75%) quarters of the fatigue life data yielded worst-case errors of 18.4%, 16.8% and 5.3%, respectively, for training on five beams and testing (predicting) on the remaining five. The worst-case prediction errors decreased to -12.4%, -13.4%, and 4.5% when trained on the AE data from six beams and tested on four. Thus, it was found that BPNN prediction accuracy was improved both by using more training data (six beams rather than five) and by training on AE data taken later (third quarter) in the fatigue life of the notched I-beams. Moreover, in an effort to simulate actual AE structural health monitoring (SHM) of bridges, AE fatigue data taken at semi-random time intervals after fatigue crack initiation were used to predict fatigue lives, which resulted in a worst case prediction error of 5.1% using five beams for training and five for testing. From all the above, it can be concluded that BPNNs trained on the AE amplitude histogram data from either the third quarter of the fatigue life or at semi-random time intervals after crack initiation can predict fatigue lives in A572-G50 bridge steel I-beams with worst case errors of ≤5% by training on the data from at least six beams. [ABSTRACT FROM AUTHOR]

Continuous attractors of Lotka–Volterra recurrent neural networks (LV RNNs) with infinite neurons are studied in this brief. A continuous attractor is a collection of connected equilibria, and it has been recognized as a suitable model for describing the encoding of continuous stimuli in neural networks. The existence of the continuous attractors depends on many factors such as the connectivity and the external inputs of the network. A continuous attractor can be stable or unstable. It is shown in this brief that a LV RNN can possess multiple continuous attractors if the synaptic connections and the external inputs are Gussian-like in shape. Moreover, both stable and unstable continuous attractors can coexist in a network. Explicit expressions of the continuous attractors are calculated. Simulations are employed to illustrate the theory. [ABSTRACT FROM PUBLISHER]

Many data mining algorithms are often found to be sensitive to the size of dataset. It may result in large memory requirements and very slow response time to execute tasks on large datasets. Thus, data reduction is an important issue in the field of data mining. This paper proposes a novel method for spatial point-data reduction. The main idea is to search a small subset of instances composed of border instances from original training set by using a modified pulse coupled neural network (PCNN) model. Original training instances are mapped into some pulse coupled neurons, and a firing algorithm is presented for determining which instances locate in border regions and filtering noisy instances. The reduced set maintains the main characteristics of original dataset and avoids the influence of noise, thus it can keep or even improve the quality of data mining results. The proposed method is a general data reduction algorithm, which can be used to improve classification, regression and clustering algorithms. The method achieves approximately linear time complexity, and can be used to process large spatial datasets. Experiments demonstrate that the proposed method is efficient and effective. [ABSTRACT FROM AUTHOR]

Abstract: The architecture and learning procedure of a novel artificial immune network, referred to as tree structured artificial immune network (TSAIN), are described in this paper. One major difference between this model and current models is that the topological structure can be strictly guaranteed as a tree, which allows to analyze the presented data (antigens) hierarchically. The other is that a novel antibody reaction mechanism inspired from the self-organizing map (SOM) is adopted in order to maintain consistency between the shape space metric and the topological metric, which is an important objective in high-dimensional data analysis. Moreover, several novel immune operators are also employed to improve the quality of the antibody population as well as to control its size. It is qualitatively demonstrated as well as quantitatively verified on a 3-D synthetic dataset and Iris dataset that TSAIN exhibits promising data visualization capability and low vector quantization error. We also use three well-known topology preservation measures to validate the topology preservation capability of our proposed model. [Copyright &y& Elsevier]

Abstract: This paper proposes a new approach to solve traveling salesman problem (TSP) by using a class of Lotka–Volterra neural networks (LVNN) with global inhibition. Some stability criteria that ensure the convergence of valid solutions are obtained. It is proved that an equilibrium state is stable if and only if it corresponds to a valid solution of the TSP. Thus, a valid solution can always be obtained whenever the network convergence to a stable state. A set of analytical conditions for optimal settings of LVNN is derived. Simulation results illustrate the theoretical analysis. [Copyright &y& Elsevier]

Abstract: Multistability is an important dynamical property in neural networks in order to enable certain applications where monostable networks could be computationally restrictive. This paper studies some multistability properties for a class of bidirectional associative memory recurrent neural networks with unsaturating piecewise linear transfer functions. Based on local inhibition, conditions for globally exponential attractivity are established. These conditions allow coexistence of stable and unstable equilibrium points. By constructing some energy-like functions, complete convergence is studied. [Copyright &y& Elsevier]

Hydroquinone generally appears in compost as a direct pollutant or an intermediate product in the aromatic pollutant biodegradation process. The requirement of quantifying its concentration calls for efficient and economical analytical methods. In this study, artificial neural networks (ANNs) were combined with a biosensor to realize nonlinear determination of hydroquinone in a complex composting system. The direct detection range for hydroquinone in compost system using biosensor reached 1.5 × 10−8 ∼ 3.6 × 10−4 M. Meanwhile, the performance of the ANN model was compared with a nonlinear regression model with respect to the simulation accuracy and adaptability to uncertainty, etc. Nonlinear range analysis could extend the usable detection range of biosensor for hydroquinone and could improve the adaptability of the detecting system in real sample determination. Results illustrated that the combined application of biosensor measurement and artificial neural network analysis was a rapid, sensitive, and robust method in a quantitative study of a composting system. This method could be a good analytical tool for further application in real sample determination in other complex environments which refer to human life and health. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a novel thinning algorithm and applies it to automatic constrained ZIP code segmentation. The segmentation method consists of two main stages: removal of rectangle boxes and location of ZIP code digits. Both the two stages are implemented on the skeleton of boxes, which is extracted by the proposed pulse coupled neural network (PCNN) based thinning algorithm. This algorithm is specially designed to merely skeletonize the boxes. At the second stage, a projection method is employed to segment ZIP code image into its constituent digits. Experimental results show that the proposed method is very efficient in segmenting ZIP code images even with noise. [Copyright &y& Elsevier]