Search

Many current medical image segmentation methods utilize convolutional neural networks (CNNs), with some extended U-Net-based networks relying on deep feature representations to achieve satisfactory results. However, due to the limited receptive fields of convolutional architectures, they are unable to explicitly model the varying range dependencies present in medical images. Recently, advancements in large kernel convolution have allowed for the extraction of a wider range of low frequency information, making this task more achievable. In this paper, we propose TBUnet for solving the problem of difficult to accurately segment lesions with heterogeneous structures and fuzzy borders, such as melanoma, colon polyps and breast cancer. The TBUnet is a pure convolutional network with three branches for extracting high frequency information, low frequency information, and boundary information, respectively. It is capable of extracting features in various areas. To fuse the feature maps from the three branches, TBUnet presents the FL (fusion layer) module, which is based on threshold and logical operation. We design the FE (feature enhancement) module on the skip-connection to emphasize the fine-grained features. In addition, our method varies the number of input channels in different branches at each stage of the network, so that the relationship between low and high frequency features can be learned. TBUnet yields 91.08 DSC on ISIC-2018 for melanoma segmentation, and achieves better performance than state-of-the-art medical image segmentation methods. Furthermore, experimental results with 82.48 DSC and 89.04 DSC obtained on the BUSI dataset and the Kvasir-SEG dataset show that TBUnet outperforms the advanced segmentation methods. Experiments demonstrate that TBUnet has excellent segmentation performance and generalisation capability. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) are widely regarded as the most effective learning tool for dealing with large datasets, and they have been successfully used in thousands of applications in a variety of fields. Based on these large datasets, they are trained to learn the relationships between various variables. The adaptive moment estimation (Adam) algorithm, a highly efficient adaptive optimization algorithm, is widely used as a learning algorithm in various fields for training DNN models. However, it needs to improve its generalization performance, especially when training with large-scale datasets. Therefore, in this paper, we propose HN Adam, a modified version of the Adam Algorithm, to improve its accuracy and convergence speed. The HN_Adam algorithm is modified by automatically adjusting the step size of the parameter updates over the training epochs. This automatic adjustment is based on the norm value of the parameter update formula according to the gradient values obtained during the training epochs. Furthermore, a hybrid mechanism was created by combining the standard Adam algorithm and the AMSGrad algorithm. As a result of these changes, the HN_Adam algorithm, like the stochastic gradient descent (SGD) algorithm, has good generalization performance and achieves fast convergence like other adaptive algorithms. To test the proposed HN_Adam algorithm performance, it is evaluated to train a deep convolutional neural network (CNN) model that classifies images using two different standard datasets: MNIST and CIFAR-10. The algorithm results are compared to the basic Adam algorithm and the SGD algorithm, in addition to other five recent SGD adaptive algorithms. In most comparisons, the HN Adam algorithm outperforms the compared algorithms in terms of accuracy and convergence speed. AdaBelief is the most competitive of the compared algorithms. In terms of testing accuracy and convergence speed (represented by the consumed training time), the HN-Adam algorithm outperforms the AdaBelief algorithm by an improvement of 1.0% and 0.29% for the MNIST dataset, and 0.93% and 1.68% for the CIFAR-10 dataset, respectively. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

Autonomous driving approaches today are mainly based on perception-planning-action modular pipelines and the End2End paradigm respectively. The End2End paradigm is a strategy that directly maps raw sensor data to vehicle control actions. This strategy is very promising and appealing because complex module design and cumbersome data labeling are avoided. Since this approach lacks a degree of interpretability, safety and practicability. we propose an autonomous driving approach based on trajectory learning using deep neural networks in this paper. In comparison to End2End algorithm, it is found that the trajectory learning algorithm performs better in autonomous driving. As for trajectory learning algorithm, the CNN_Raw-RNN network structure is established, which is verified to be more effective than the original CNN_LSTM network structure. Besides, we propose an autonomous driving architecture of a pilot and copilot combination. The pilot is responsible for trajectory prediction via imitation learning with labeled driving trajectories, while the copilot is a safety module that is employed to verify the effectiveness of the vehicle trajectory by the results of the semantic segmentation auxiliary task. The proposed autonomous driving architecture is verified with a real car on urban roads without manual intervention within 40 km. [ABSTRACT FROM AUTHOR]

In many machine learning applications and algorithms, the algorithm performance and accuracy are highly dependent on the metric used to measure the distance between different samples. Therefore, learning a distance metric specific to the data can improve these algorithms' performance. This paper proposes an unrestricted deep metric learning framework based on neural networks' interaction for learning metrics in latent space. The proposed method is inspired by generative neural nets (GANs), in which two neural nets are working together to learn true data distribution. In our method, one network plays the role of a supervisor for another network, a feature learning auto-encoder. Its task is to learn transformation to latent space in which data have more meaningful distance and separability. i.e., the supervisor gets the output of the auto-encoder and sends feedback to modify its weights. They interact with each other interleavingly. Several experiments were conducted on four datasets, such as MNIST, GISETTE, Winnipeg Cropland Classification (WCC), and swarm behavior, from different application domains, to evaluate the proposed method's performance. The results show that we can force auto-encoder to learn label information to project data into a latent space with better separability by using our approach. In addition to better class discrimination, the proposed method is far faster than normal auto-encoders during feature learning and has much less training time in the classification phase. [ABSTRACT FROM AUTHOR]

Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago. [ABSTRACT FROM AUTHOR]

Although tendon-driven continuum manipulators have been extensively researched, how to realize tip contact force sensing in a more general and efficient way without increasing the diameter is still a challenge. Rather than use a complex modeling approach, this paper proposes a general tip contact force-sensing method based on a recurrent neural network that takes the tendons' position and tension as the input of a recurrent neural network and the tip contact force of the continuum manipulator as the output and fits this static model by means of machine learning so that it may be used as a real-time contact force estimator. We also designed and built a corresponding three-degree-of-freedom contact force data acquisition platform based on the structure of a continuum manipulator designed in our previous studies. After obtaining training data, we built and compared the performances of a multi-layer perceptron-based contact force estimator as a baseline and three typical recurrent neural network-based contact force estimators through TensorFlow framework to verify the feasibility of this method. We also proposed a manually decoupled sub-estimators algorithm and evaluated the advantages and disadvantages of those two methods. [ABSTRACT FROM AUTHOR]

In recent decades, researches on optimizing the parameter of the artificial neural network (ANN) model has attracted significant attention from researchers. Hybridization of superior algorithms helps improving optimization performance and capable of solving complex applications. As a traditional gradient-based learning algorithm, ANN suffers from a slow learning rate and is easily trapped in local minima when training techniques such as gradient descent (GD) and back-propagation (BP) algorithm are used. The characteristics of randomization and selection of the best or near-optimal solution of metaheuristic algorithm provide an effective and robust solution; therefore, it has always been used in training of ANN to improve and overcome the above problems. New metaheuristic algorithms are proposed every year. Therefore, the review of its latest developments is essential. This article attempts to summarize the metaheuristic algorithms which have been proposed from the year 1975 to 2020 from various journals, conferences, technical papers, and books. The comparison of the popularity of the metaheuristic algorithm is presented in two time frames, such as algorithms proposed in the recent 20 years and those proposed earlier. Then, some of the popular metaheuristic algorithms and their working principle are reviewed. This article further categorizes the latest metaheuristic search algorithm in the literature to indicate their efficiency in training ANN for various industry applications. More and more researchers tend to develop new hybrid optimization tools by combining two or more metaheuristic algorithms to optimize the training parameters of ANN. Generally, the algorithm's optimal performance must be able to achieve a fine balance of their exploration and exploitation characteristics. Hence, this article tries to compare and summarize the properties of various metaheuristic algorithms in terms of their convergence rate and the ability to avoid the local minima. This information is useful for researchers working on algorithm hybridization by providing a good understanding of the convergence rate and the ability to find a global optimum. [ABSTRACT FROM AUTHOR]

We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstructed from magnitude constraints and general characteristics (sparsity, support, etc.). Instead of taking gradient steps, the optimizer in the constraint based approach, called relaxed–reflect–reflect (RRR), derives its steps from projections to local constraints. In neural networks one such projection makes the minimal modification to the inputs x, the associated weights w, and the pre-activation value y at each neuron, to satisfy the equation x ⋅ w = y . These projections, along with a host of other local projections (constraining pre- and post-activations, etc.) can be partitioned into two sets such that all the projections in each set can be applied concurrently—across the network and across all data in the training batch. This partitioning into two sets is analogous to the situation in phase retrieval and the setting for which the general purpose RRR optimizer was designed. Owing to the novelty of the method, this paper also serves as a self-contained tutorial. Starting with a single-layer network that performs nonnegative matrix factorization, and concluding with a generative model comprising an autoencoder and classifier, all applications and their implementations by projections are described in complete detail. Although the new approach has the potential to extend the scope of neural networks (e.g. by defining activation not through functions but constraint sets), most of the featured models are standard to allow comparison with stochastic gradient descent. [ABSTRACT FROM AUTHOR]

The paper proposes the concept of inverse P-augmented matrix, and gives its structure; the inverse P-augmented matrix is obtained by improving the common augmented matrix; under certain condition, the inverse P-augmented matrix is reduced to the common augmented matrix. Inverse P-sets is the theoretical basis of proposing inverse P-augmented matrix, which is a new set model with dynamic feature. The paper gives the introduction of inverse-P set, the generation method of inverse P-augmented matrix and the relation between inverse P-augmented matrix and common augmented matrix, and gives the application of inverse P-augmented matrix in the dynamic findings of unknown information by virtue of these studies. [ABSTRACT FROM AUTHOR]

Due to the huge amount of data being generating from different sources, the analyzing and extracting of useful information from these data becomes a very complex task. The difficulty of dealing with big data optimization problems comes from many factors such as the high number of features, and the existing of lost data. The feature selection process becomes an important step in many data mining and machine learning algorithms to reduce the dimensionality of the optimization problems and increase the performance of the classification or clustering algorithms. In this paper, a set of hybrid and efficient genetic algorithms are proposed to solve feature selection problem, when the handled data has a large feature size. The proposed algorithms use a new gene-weighted mechanism that can adaptively classify the features into strong relative features, weak or redundant features, and unstable features during the evolution of the algorithm. Based on this classification, the proposed algorithm gives the strong features high priority and the weak features less priority when generating new candidate solutions. In the same time, the proposed algorithm tries to more concentrate on unstable features that sometimes appear and sometimes disappear from the best solutions of the population. The performance of proposed algorithms is investigated by using different datasets and feature selection algorithms. The results show that our proposed algorithms can outperform the other feature selection algorithms and effectively enhance the classification performance over the tested datasets. [ABSTRACT FROM AUTHOR]

With age, our blood vessels are prone to aging, which induces cardiovascular disease. As an important basis for diagnosing heart disease and evaluating heart function, the electrocardiogram (ECG) records cardiac physiological electrical activity. Abnormalities in cardiac physiological activity are directly reflected in the ECG. Thus, ECG research is conducive to heart disease diagnosis. Considering the complexity of arrhythmia detection, we present an improved convolutional neural network (CNN) model for accurate classification. Compared with the traditional machine learning methods, CNN requires no additional feature extraction steps due to the automatic feature processing layers. In this paper, an improved CNN is proposed to automatically classify the heartbeat of arrhythmia. Firstly, all the heartbeats are divided from the original signals. After segmentation, the ECG heartbeats can be inputted into the first convolutional layers. In the proposed structure, kernels with different sizes are used in each convolution layer, which takes full advantage of the features in different scales. Then a max-pooling layer followed. The outputs of the last pooling layer are merged and as the input to fully-connected layers. Our experiment is in accordance with the AAMI inter-patient standard, which included normal beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F), and unknown beats (Q). For verification, the MIT arrhythmia database is introduced to confirm the accuracy of the proposed method, then, comparative experiments are conducted. The experiment demonstrates that our proposed method has high performance for arrhythmia detection, the accuracy is 99.06%. When properly trained, the proposed improved CNN model can be employed as a tool to automatically detect different kinds of arrhythmia from ECG. [ABSTRACT FROM AUTHOR]

Liao et al. (Neurocomputing 128:81-87, 2014) proposed a meta-learning approach to extreme learning machine (Meta-ELM), which can obtain good generalization performance by training multiple ELMs. However, one of its open problems is overfitting when minimizing training error. In this paper, we propose an improved meta-learning model of ELM (improved Meta-ELM) to handle the problem. The improved Meta-ELM architecture is composed of some base ELMs which are error feedback incremental extreme learning machine (EFI-ELM) and the top ELM. The improved Meta-ELM includes two stages. First, each base ELM with EFI-ELM is trained on a subset of training data. Then, the top ELM learns with the base ELMs as hidden nodes. Simulation results on some artificial and benchmark datasets show that the proposed improved Meta-ELM model is more feasible and effective than Meta-ELM. [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]

Deep neural networks (DNNs) is one of the most popular machine learning methods and is widely used in many modern applications. The training process of DNNs is a time-consuming process. Accelerating the training of DNNs has been the focus of many research works. In this paper, we speed up the training of DNNs applied for automatic speech recognition and the target architecture is heterogeneous (CPU + MIC). We apply asynchronous methods for I/O and communication operations and propose an adaptive load balancing method. Besides, we also employ a momentum idea to speed up the convergence of the gradient descent algorithm. Experimental results show that our optimized algorithm is able to acquire a 20-fold speedup on a CPU + MIC platform compared with the original sequential algorithm on a single-core CPU. [ABSTRACT FROM AUTHOR]

With the rapid development of machine learning, artificial intelligence (AI) has drawn much more attention. Under this circumstances, abstract strategy games, such as chess, checkers and Go, have been a fascinating problem of AI research. Most of the existing state-of-the-art Go programs used deep neural network technology, like convolutional neural networks (CNNs). However, CNNs require multiple iterations to optimize weights and spend a lot of training time. Therefore, in this paper, in order to solve the above shortcomings, we propose a new learning algorithm ECNN, which integrates CNNs with extreme learning machine (ELM). We remove pooling layers of CNNs and insert ELM layers between convolutional layers. The newly added ELM layers will be updated in back-propagation process, and they accelerate the convergence of weights in CNNs. Therefore, our ECNN can reduce the training time of CNNs. Further, we propose ECNN-Go algorithm, which applies ECNN to Go game. Because of the advantage of ECNN, ECNN-Go algorithm has the fast learning speed to make move prediction in Go game. Finally, the experimental results show the efficiency and accuracy of ECNN algorithm and demonstrate the strength of ECNN-Go. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is a non-iterative algorithm for training single-hidden layer feed-forward networks, whose training speed is much faster than those of conventional neural networks. However, its objective is only to minimize the empirical risk, which may cause overfitting easily. To overcome this defect, this paper proposes a novel algorithm named LGE2LM based on the localized generalization error model which provides an upper bound of generalization error through adopting the stochastic sensitivity. LGE2LM aims to improve the generalization capability of ELM by using the regularization technique which makes a trade-off between the empirical risk and the stochastic sensitive measure. The essence of LGE2LM is a quadratic problem without iterative process. Similar to ELM, all the parameters of this new algorithm are obtained without tuning, which makes the efficiency of LGE2LM much higher than those of traditional neural networks. Several experiments conducted on both artificial and real-world datasets show that LGE2LM has much better generalization capability and stronger robustness in comparison with ELM. [ABSTRACT FROM AUTHOR]

Cluster analysis as an important function of the data mining has made great progress in recent years a series of methods for analysis of accuracy provides a solid foundation. This paper proposes the novel pattern clustering algorithm based on particle swarm optimization joint adaptive wavelet neural network model. Nonlinear adaptive filter has the stronger ability of that signal processing. However, due to complicated calculation of the nonlinear adaptive filter, the actual use of linear adaptive filter is still. To deal with this challenge, we integrate the wavelet neural network for modification. Usually, the wavelet neural network learning process using the gradient descent method, even if the error function that along the negative gradient direction, and which requires the step length direction along the negative gradient direction. As well, we revise the PSO to enhance the wavelet NN in the process of search, the equilibrium relation between the global search ability and local search ability for the success of the algorithm plays an important role. With this modification, our method obtains the better performance. The experimental result shows the feasibility and the effectiveness of the method compared with the other latest and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Posterior capsule opacification (PCO) is the most common complication of cataract surgery, occurring in up to 50% of patients by 2-3 years after the operation [Spalton in Eye 13(Pt 3b):489-492, ]. This paper proposes a new approach for the assessment of PCO digital images. The approach deploys an unsupervised learning technique for clustering image pixels into different regions based on chromatic attributes. The innovative aspect of this paper lies in proposing the number of regions in a clustered image as a measurement tool for assessing the PCO. Experiments using synthetic data confirmed the plausibility of this approach. A series of experiments conducted on real PCO images demonstrated the robustness and stability of the proposed algorithm. Finally, the comparison of our method's assessment with medical expert evaluation reveals a very reasonable concordance. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive control algorithm is proposed for a class of robot manipulator systems with unknown functions and dead-zone input by using a reinforcement learning scheme. The parameters of the dead zone are supposed to be unknown but bounded. The unknown functions can be approximated based on the neural networks, which is one part of the reinforcement learning scheme, namely an action network. The other part is called critic network which is used to approximate the reinforcement signal. Then, the prominent advantage of the proposed approach is that an optimal control input can be obtained by using two networks compared with the results of robot manipulator with dead zone: an additional term is given to compensate for the effect of the dead zone, and a special design procedure to solve the difficulties in constructing the controllers and adaptation laws. Based on the Lyapunov analysis theory, all the signals of the closed-loop system are proved to be bounded and the system output can track the reference signal to a bounded compact set. Finally, a simulation example is given to illustrate the effectiveness of the approach. [ABSTRACT FROM AUTHOR]

Sample misalignment exerts an important influence on training a rapid and accurate human detector, and it is a difficult problem to tackle with due to human articulation or manual annotation errors. Multiple instances learning method is an effective tool to deal with this difficulty without manual correction. In this paper, firstly, we propose a variable granularity HOG-CSLBP feature, which combines the human shape information with local texture information, and encodes spatial relationship in different granularity to improve its discriminative ability. Our new feature takes an advantage of the mutual complementarities of histogram of gradient and center-symmetric local binary patterns feature, which is adept at modeling human. Secondly, we present a Gentle MILBoost algorithm which utilizes the Newton update technique to get an optimal weak classifier that is able to discriminate complex distribution and is more stable in numerical computation. Experimental results based on INRIA, MIT-CBCL and TUD-Brussels datasets have showed superior performance of our method. Moreover, our method can achieve real-time speed in real application. [ABSTRACT FROM AUTHOR]

Distributed training allows individual entities to benefit from the training sets owned by other entities. Nevertheless, distributed training also causes serious privacy concerns. Hence, it is highly important to protect privacy in distributed training. In this paper, we study the privacy protection in distributed training of neural network ensembles. We design a privacy-preserving distributed algorithm for training neural network ensembles using AdaBoost.M2. We also analyze the security and complexity of our algorithm. Furthermore, we perform experiments on two data sets of the UCI repository to verify the algorithm's effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we propose an extreme learning machine (ELM) with tunable activation function (TAF-ELM) learning algorithm, which determines its activation functions dynamically by means of the differential evolution algorithm based on the input data. The main objective is to overcome the problem dependence of fixed slop of the activation function in ELM. We mainly considered the issue of processing of benchmark problems on function approximation and pattern classification. Compared with ELM and E-ELM learning algorithms with the same network size or compact network configuration, the proposed algorithm has improved generalization performance with good accuracy. In addition, the proposed algorithm also has very good performance in the TAF neural networks learning algorithms. [ABSTRACT FROM AUTHOR]

Ensemble learning has gained considerable attention in different learning tasks including regression, classification, and clustering problems. One of the drawbacks of the ensemble is the high computational cost of training stages. Resampling local negative correlation (RLNC) is a technique that combines two well-known methods to generate ensemble diversity-resampling and error negative correlation-and a fine-grain parallel approach that allows us to achieve a satisfactory balance between accuracy and efficiency. In this paper, we introduce a structure of the virtual machine aimed to test diverse selection strategies of parameters in neural ensemble designs, such as RLNC. We assess the parallel performance of this approach on a virtual machine cluster based on the full virtualization paradigm, using speedup and efficiency as performance metrics, for different numbers of processors and training data sizes. [ABSTRACT FROM AUTHOR]

Fuzzy neural network (FNN) has long been recognized as an efficient and powerful learning machine for general machine learning problems. Recently, Wilcoxon fuzzy neural network (WFNN), which generalizes the rank-based Wilcoxon approach for linear parametric regression problems to nonparametric neural network, was proposed aiming at improving robustness against outliers. FNN and WFNN are nonparametric models in the sense that they put no restrictions, except possibly smoothness, on the functional form of the regression function. However, they may be difficult to interpret and, even worse, yield poor estimates with high computational cost when the number of predictor variables is large. To overcome this drawback, semiparametric models have been proposed in statistical regression theory. A semiparametric model keeps the easy interpretability of its parametric part and retains the flexibility of its nonparametric part. Based on this, semiparametric FNN and semiparametric WFNN will be proposed in this paper. The learning rules are based on the backfitting procedure frequently used in semiparametric regression. Simulation results show that the semiparametric models perform better than their nonparametric counterparts. [ABSTRACT FROM AUTHOR]

In this paper, we present nonmonotone variants of the Levenberg-Marquardt (LM) method for training recurrent neural networks (RNNs). These methods inherit the benefits of previously developed LM with momentum algorithms and are equipped with nonmonotone criteria, allowing temporal increase in training errors, and an adaptive scheme for tuning the size of the nonmonotone slide window. The proposed algorithms are applied to training RNNs of various sizes and architectures in symbolic sequence-processing problems. Experiments show that the proposed nonmonotone learning algorithms train more effectively RNNs for sequence processing than the original monotone methods. [ABSTRACT FROM AUTHOR]

This paper proposes a novel steam valving controller using radial basis function (RBF) networks-based approximate model method. Approximate model method is a kind of direct linearization approach that is derived based on the approximation of the plant's input-output model via Taylor expansion. RBF networks are used to identify the plant to implement the approximate model control law. In order to improve the performance of the approximate model controller, RBF networks weights are adjusted online using BP algorithms with an adaptive learning rate. Several simulations results demonstrate the effectiveness of the proposed controller for team valving control. [ABSTRACT FROM AUTHOR]

This paper deals with the parallel layer perceptron (PLP) complexity control, bias and variance dilemma, using a multiobjective (MOBJ) training algorithm. To control the bias and variance the training process is rewritten as a bi-objective problem, considering the minimization of both training error and norm of the weight vector, which is a measure of the network complexity. This method is applied to regression and classification problems and compared with several other training procedures and topologies. The results show that the PLP MOBJ training algorithm presents good generalization results, outperforming traditional methods in the tested examples. [ABSTRACT FROM AUTHOR]

Few studies in the literature have researched the use of surface electromyography (sEMG) for motor assessment post-stroke due to the complexity of this type of signal. However, recent advances in signal processing and machine learning have provided fresh opportunities for analyzing complex, non-linear, non-stationary signals, such as sEMG. This paper presents a method for identification of the upper limb movements from sEMG signals using a combination of digital signal processing, that is discrete wavelet transform, and the enhanced probabilistic neural network (EPNN). To explore the potential of sEMG signals for monitoring motor rehabilitation progress, this study used sEMG signals from a subset of movements of the Arm Motor Ability Test (AMAT) as inputs into a movement classification algorithm. The importance of a particular frequency domain feature, that is the ratio of the mean absolute values between sub-bands, was discovered in this work. An average classification accuracy of 75.5% was achieved using the proposed approach with a maximum accuracy of 100%. The performance of the proposed method was compared with results obtained using three other classification algorithms: support vector machine (SVM), k-Nearest Neighbors (k-NN), and probabilistic neural network (PNN) in terms of sEMG movement classification. The study demonstrated the capability of using upper limb sEMG signals to identify and distinguish between functional movements used in standard upper limb motor assessments for stroke patients. The classification algorithm used in the proposed method, EPNN, outperformed SVM, k-NN, and PNN. [ABSTRACT FROM AUTHOR]

Existing brain region segmentation algorithms based on deep convolutional neural networks (CNN) are inefficient for object boundary segmentation. In order to enhance the segmentation accuracy of brain tissue, this paper proposed an object region segmentation algorithm that combines pixel-level information and semantic information. Firstly, we extract semantic information by CNN with the attention module and get the coarse segmentation results through a specific pixel-level classifier. Then, we exploit conditional random fields to model the relationship between the underlying pixels so as to get local features. Finally, the semantic information and the local pixel-level information are respectively used as the unary potential and the binary potential of the Gibbs distribution, and the combination of both can obtain the fine region segmentation algorithm based on the fusion of pixel-level information and the semantic information. A large number of qualitative and quantitative test results show that our proposed algorithm has higher precision than the existing state-of-the-art deep feature models, which can better solve the problem of rough edge segmentation and produce good 3D visualization effect. [ABSTRACT FROM AUTHOR]

Nowadays, the most frequent cancer in women is breast cancer (malignant tumor). If breast cancer is detected at the beginning stage, it can often be cured. Many researchers proposed numerous methods for early prediction of this Cancer. In this paper, we proposed feature ensemble learning based on Sparse Autoencoders and Softmax Regression for classification of Breast Cancer into benign (non-cancerous) and malignant (cancerous). We used Breast Cancer Wisconsin (Diagnostic) medical data sets from the UCI machine learning repository. The proposed method is assessed using various performance indices like true classification accuracy, specificity, sensitivity, recall, precision, f measure, and MCC. Simulation and result proved that the proposed approach gives better results in terms of different parameters. The prediction results obtained by the proposed approach were very promising (98.60% true accuracy). In addition, the proposed method outperforms the Stacked Sparse Autoencoders and Softmax Regression based (SSAE-SM) model and other State-of-the-art classifiers in terms of various performance indices. Experimental simulations, empirical results, and statistical analyses are also showing that the proposed model is an efficient and beneficial model for classification of Breast Cancer. It is also comparable with the existing machine learning and soft computing approaches present in the related literature. [ABSTRACT FROM AUTHOR]

Blood pressure (BP) is a bio-physiological signal that can provide very useful information regarding human's general health. High or low blood pressure or its rapid fluctuations can be associated to various diseases or conditions. Nowadays, high blood pressure is considered to be an important health risk factor and major cause of various health problems worldwide. High blood pressure may precede serious heart diseases, stroke and kidney failure. Accurate blood pressure measurement and monitoring plays fundamental role in diagnosis, prevention and treatment of these diseases. Blood pressure is usually measured in the hospitals, as a part of a standard medical routine. However, there is an increasing demand for methodologies, systems as well as accurate and unobtrusive devices that will permit continuous blood pressure measurement and monitoring for a wide variety of patients, allowing them to perform their daily activities without any disturbance. Technological advancements in the last decade have created opportunities for using various devices as a part of ambient assisted living for improving quality of life for people in their natural environment. The main goal of this paper is to provide a comprehensive review of various methodologies for continuous cuff-less blood pressure measurement, as well as to evidence recently developed devices and systems for continuous blood pressure measurement that can be used in ambient assisted living applications. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new Internet of Things (IoT) based predictive modelling by using fuzzy cluster based augmentation and classification for predicting the lung cancer disease through continuous monitoring and also to improve the healthcare by providing medical instructions. Here, the fuzzy clustering method is used and which is based on transition region extraction for effective image segmentation. Moreover, Fuzzy C-Means Clustering algorithm is used to categorize the transitional region features from the feature of lung cancer image. In this work, Otsu thresholding method is used for extracting the transition region from lung cancer image. Moreover, the right edge image and the morphological thinning operation are used for enhancing the performance of segmentation. In addition, the morphological cleaning and the image region filling operations are performed over an edge lung cancer image for getting the object regions. In addition, we also propose a new incremental classification algorithm which combines the existing Association Rule Mining (ARM), the standard Decision Tree (DT) with temporal features and the CNN. The experiments have been conducted by using the standard images that are collected from database and the current health data which are collected from patient through IoT devices. The results proved that the performance of the proposed prediction model which is able to achieve the better accuracy when it is compared with other existing prediction model. [ABSTRACT FROM AUTHOR]

Disease diagnosis from medical images has become increasingly important in medical science. Abnormality identification in retinal images has become a challenging task in medical science. Effective machine learning and soft computing methods should be used to facilitate Diabetic Retinopathy Diagnosis from Retinal Images. Artificial Neural Networks are widely preferred for Diabetic Retinopathy Diagnosis from Retinal Images. It was observed that the conventional neural networks especially the Hopfield Neural Network (HNN) may be inaccurate due to the weight values are not adjusted in the training process. This paper presents a new Modified Hopfield Neural Network (MHNN) for abnormality classification from human retinal images. It relies on the idea that both weight values and output values can be adjusted simultaneously. The novelty of the proposed method lies in the training algorithm. In conventional method, the weights remain fixed but the weights are changing in the proposed method. Experimental performed on the Lotus Eye Care Hospital containing 540 images collected showed that the proposed MHNN yields an average sensitivity and specificity of 0.99 and accuracy of 99.25%. The proposed MHNN is better than HNN and other neural network approaches for Diabetic Retinopathy Diagnosis from Retinal Images. [ABSTRACT FROM AUTHOR]

Skeletal bone age assessment is a widely used standard procedure in both disease detection and growth prediction for children in endocrinology. Conventional manual assessment methods mainly rely on personal experience in observing X-ray images of left hand and wrist to calculate bone age, which show some intrinsic limitations from low efficiency to unstable accuracy. To address these problems, some automated methods based on image processing or machine learning have been proposed, while their performances are not satisfying enough yet in assessment accuracy. Motivated by the remarkable success of deep learning (DL) techniques in the fields of image classification and speech recognition, we develop a deep automated skeletal bone age assessment model based on convolutional neural networks (CNNs) and support vector regression (SVR) using multiple kernel learning (MKL) algorithm to process heterogeneous features in this paper. This deep framework has been constructed, not only exploring the X-ray images of hand and twist but also some other heterogeneous information like race and gender. The experiment results prove its better performance with higher bone age assessment accuracy on two different data sets compared with the state of the art, indicating that the fused heterogeneous features provide a better description of the degree of bones' maturation. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) signal is a process that records the heart rate by using electrodes and detects small electrical changes for each heat rate. It is used to investigate some types of abnormal heart function including arrhythmias and conduction disturbance. In this paper the proposed method is used to classify the ECG signal by using classification technique. First the Input signal is preprocessed by using filtering method such as low pass, high pass and butter worth filter to remove the high frequency noise. Butter worth filter is to remove the excess noise in the signal. After preprocessing peak points are detected by using peak detection algorithm and extract the features for the signal are extracted using statistical parameters. Finally, extracted features are classified by using SVM, Adaboost, ANN and Naïve Bayes classifier to classify the ECG signal database into normal or abnormal ECG signal. Experimental result shows that the accuracy of the SVM, Adaboost, ANN and Naïve Bayes classifier is 87.5%, 93%, 94 and 99.7%. Compared to other classifier naïve bayes classifier accuracy is high. [ABSTRACT FROM AUTHOR]

Nature presents an infinite source of inspiration for computational models and paradigms, in particular for researchers associated with the area known as natural computing. The simultaneous optimization of the architectures and weights of artificial neural networks (ANNs) through biologically inspired algorithms is an interesting approach for obtaining efficient networks with relatively good generalization capabilities. This methodology constitutes a concordance between a low structural complexity model and low training error rates. Currently, complexity and high error rates are the leading issues faced in the development of clinical decision support systems (CDSSs) for pregnancy care. Hence, in this paper the use of a biologically inspired technique, known as particle swarm optimization (PSO), is proposed for reducing the computational cost of the ANN-based method referred to as the multilayer perceptron (MLP), without reducing its precision rate. The results show that the PSO algorithm is able to improve computational model performance, showing lower validation error rates than the conventional approach. This technique can select the best parameters and provide an efficient solution for training the MLP algorithm. The proposed nature-inspired algorithm and its parameter adjustment method improve the performance and precision of CDSSs. This technique can be applied in electronic health (e-health) systems as a useful tool for handling uncertainty in the decision-making process related to high-risk pregnancy. The proposed method outperformed, on average, other approaches by 26.4% in terms of precision and 14.9% in terms of the true positive ratio (TPR), and showed a reduction of 35.4% in the false positive ratio (FPR). Furthermore, this method was superior to the MLP algorithm in terms of precision and area under the receiver operating characteristic curve by 2.3 and 10.2%, respectively, when applied to the delivery outcome for pregnant women. [ABSTRACT FROM AUTHOR]