Search

In the process of Human-robot skill transfer, we require the robot to reproduce the trajectory of teacher and expect that the robot can generalize the learned trajectory. For the trajectory after generalization, we expect that the robot arm can accurately track. However, because the model of the robot can not be accurately obtained, some researchers have proposed using a neural network to approximate the unknown term. The parameters of the traditional RBF neural network are usually selected through the empirical and trial-and-error method, which maybe biased and inefficient. In addition, due to the end-effector of the mechanical arm trajectory will be constantly changing according to the needs of the task, when the neural network of compact set cannot contain the whole input vector, the neural network cannot achieve the ideal approximation effect. In this paper, the broad neural network is used to approximate the unknown terms of the robot. This method can reuse the motion controller that has been learned and complete other motions in the robot operating space without relearning its weight parameters. In this paper, the effectiveness of the proposed method is proved by the ultrasound scanning task.

This paper proposes a hybrid architecture based on neural networks, fuzzy systems, and n-uninorms for solving pattern classification problems, termed as ENFS-Uni0 (short for evolving neuro-fuzzy system based on uni-nullneurons). The model can produce knowledge in an on-line (single-pass) and evolving learning context in a particular form of neuro-fuzzy rules representing the dependencies among input features through IF-THEN type relations. The rules antecedents are thereby realized through uni-nullneurons, which are constructed from n-uninorms, leading to the possibility to express both, AND- and OR-connections (and a mixture of these) among the single antecedent parts of a rule (and thus achieving an advanced interpretability aspect of the rules). The neurons’ evolution is done through an extended version of an autonomous data partition method (ADPA). On-line interpretation of the timely evolution of rules is addressed by (i) a concept for tracking the degree of changes of the rules over data stream samples, which may indicate experts/operators how much dynamics is in the process and may be used as a structural active learning component to request operator’s feedback in the case of significant changes and (ii) a concept for updating feature weights incrementally. These weights express the (possibly changing) impact degrees of features on the classification problem: features with low weights can be seen as unimportant and masked out when showing rules to an expert ( → rule length reduction). The rules’ consequents are represented by certainty vectors and are recursively updated by an indicator-based recursive weighted least squares (I-RWLS) approach (one RWLS estimator per class) where the weights are given through the neuron activation levels in order to gain stable local learning. The model proposed in this paper was successfully compared to related hybrid and evolving approaches in the literature for classifying binary and multi-class patterns. The results obtained by the proposed model show an outperformance of the related works in terms of higher accuracy trend lines over time, while offering a high degree of interpretability through coherent neuro-fuzzy rules to solve the classification problems.

With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git.

Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pretrained on a large and versatile dataset (ImageNet). However, in most research, the CNN architecture for feature extraction is chosen arbitrarily, without justification. This paper aims at providing insight on the use of pretrained CNN features for image clustering (IC). First, extensive experiments are conducted and show that, for a given dataset, the choice of the CNN architecture for feature extraction has a huge impact on the final clustering. These experiments also demonstrate that proper extractor selection for a given IC task is difficult. To solve this issue, we propose to rephrase the IC problem as a multi-view clustering (MVC) problem that considers features extracted from different architectures as different "views" of the same data. This approach is based on the assumption that information contained in the different CNN may be complementary, even when pretrained on the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. This approach is tested on nine natural image datasets, and produces state-of-the-art results for IC., Comment: 21 pages, 16 figures, 10 tables, preprint of our paper published in Neurocomputing

In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far. This is ensured by using a sequential pair-wise discriminator that shares weights with the encoder that is trained with a suitable loss function. Our loss function penalizes paraphrase sentence embedding distances from being too large. This loss is used in combination with a sequential encoder-decoder network. We also validated our method by evaluating the obtained embeddings for a sentiment analysis task. The proposed method results in semantic embeddings and outperforms the state-of-the-art on the paraphrase generation and sentiment analysis task on standard datasets. These results are also shown to be statistically significant., Comment: This work is an extension of our COLING-2018 paper arXiv:1806.00807

Person reidentification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views in a surveillance camera network. It has recently been validated that reranking can achieve remarkable performance improvements in person ReID systems. However, current reranking approaches either require feedback from users or suffer from burdensome computational costs. In this paper, we propose to exploit a density-adaptive smooth kernel technique to achieve efficient and effective reranking. Specifically, we adopt a smooth kernel function to formulate the neighbor relationships among data samples with a density-adaptive parameter. Based on this new formulation, we present two simple yet effective reranking methods, termed \emph{inverse} density-adaptive kernel based reranking (inv-DAKR) and \emph{bidirectional} density-adaptive kernel based reranking (bi-DAKR), in which the local density information in the vicinity of each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR methods to incorporate the available extra probe samples and demonstrate that when and why these extra probe samples are able to improve the local neighborhood and thus further refine the ranking results. Extensive experiments are conducted on six benchmark datasets, including: PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. The experimental results demonstrate that our proposals are effective and efficient., 39 pages, 18 figures and 12 tables. This paper is an extended version of our preliminary work on ICPR 2018

Manual annotation of video segmentation datasets requires an immense amount of human effort, thus, reduction of human annotation costs is an active topic of research. While many papers deal with the propagation of masks through frames of a video, only a few results attempt to optimize annotation task selection. In this paper we present a deep learning based solution to the latter problem and train it using Reinforcement Learning. Our approach utilizes a modified version of the Dueling Deep Q-Network sharing weight parameters across the temporal axis of the video. This technique enables the trained agent to select annotation tasks from the whole video. We evaluate our annotation task selection method by means of a hierarchical supervoxel segmentation based mask propagation algorithm.

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-Extension., This paper has been accepted by Neurocomputing

Feature selection plays an important role in reducing irrelevant and redundant features, while retaining the underlying semantics of selected ones. An effective feature selection method is expected to result in a significantly reduced subset of the original features without sacrificing the quality of problem-solving (e.g., classification). In this paper, a non-unique decision measure is proposed that captures the degree of a given feature subset being relevant to different categories. This helps to represent the uncertainty information in the boundary region of a granular model, such as rough sets or fuzzy-rough sets in an efficient manner. Based on this measure, the paper further introduce a differentiation entropy as an evaluator of feature subsets to implement a novel feature selection algorithm. The resulting feature selection method is capable of dealing with either nominal or real-valued data. Experimental results on both benchmark data sets and a real application problem demonstrate that the features selected by the proposed approach outperform those attained by state-of-the-art feature selection techniques, in terms of both the size of feature reduction and the classification accuracy.

Facial expressions play an important role during communications, allowing information regarding the emotional state of an individual to be conveyed and inferred. Research suggests that automatic facial expression recognition is a promising avenue of enquiry in mental healthcare, as facial expressions can also reflect an individual's mental state. In order to develop user-friendly, low-cost and effective facial expression analysis systems for mental health care, this paper presents a novel deep convolution network based emotion analysis framework to support mental state detection and diagnosis. The proposed system is able to process facial images and interpret the temporal evolution of emotions through a new solution in which deep features are extracted from the Fully Connected Layer 6 of the AlexNet, with a standard Linear Discriminant Analysis Classifier exploited to obtain the final classification outcome. It is tested against 5 benchmarking databases, including JAFFE, KDEF,CK+, and databases with the images obtained ‘in the wild’ such as FER2013 and AffectNet. Compared with the other state-of-the-art methods, we observe that our method has overall higher accuracy of facial expression recognition. Additionally, when compared to the state-of-the-art deep learning algorithms such as Vgg16, GoogleNet, ResNet and AlexNet, the proposed method demonstrated better efficiency and has less device requirements. The experiments presented in this paper demonstrate that the proposed method outperforms the other methods in terms of accuracy and efficiency which suggests it could act as a smart, low-cost, user-friendly cognitive aid to detect, monitor, and diagnose the mental health of a patient through automatic facial expression analysis.

Hand gestures are quite suitable for space human-robot interaction (SHRI) because of their natural and convenient features. While the detection and localization of hands are the premise and foundation for SHRI based on hand gestures. But hand gestures are very complicated and hand sizes are very small in some images. These problems make the robust real-time hand detection and local- ization very difficult. In this paper, a feature-map-fused single shot multibox detector (FF-SSD) which is a deep learning network is designed to deal with the problems of hand detection and localization in SHRI. First, the background of the method is introduced in this paper, including an astronaut assistant robot platform, the difficulties of hand detection and localization, and introduction of the state-of-the-art deep learning networks for object detection and localiza- tion. Then, the FF-SSD is proposed for detecting and localizing hands especially pony-size hands. This network magentatakes into consideration both accuracy and speed with balanced performance. And in the experiment part, the FF-SSD is trained and tested on hand databases which include a homemade database and two public databases. At last, the superiority of the proposed method is demonstrated compared with the state-of-the-art methods.

The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of the discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol., This paper has been accepted for publication in Neurocomputing 2019. arXiv admin note: substantial text overlap with arXiv:1809.09081

In this paper, we address a challenging task in real-word applications, i.e., automatic reading recognition for pointer meters, called PRM. 1 This application is valuable in the fields of military, industry, and aerospace. However, the accuracy of recognizing the readings of pointer meters by machine vision is, oftentimes, affected by several factors, such as uneven illumination in each image, large range variation of illumination in different images, complex backgrounds, tilting of pointer meters, image blur, and scale change, resulting in the recognized readings with unacceptable accuracy. In this paper, a new robust approach to reading recognition of pointer meters is proposed. The proposed method consists of three main contributions: (1) constructing a novel deep learning algorithm in which the PrRoIPooling is used in lieu of the RoiAlign in the existing Mask-RCNN, (2) classifying the type of pointer meters while fitting the pointer binary mask, and (3) calculating the readings of pointer meters by the proposed angle method. In addition, we also report and release a new dataset for the community. Experiments show that the new algorithm can significantly improve the accuracy of the recognized readings of pointer meters, meanwhile, the proposed approach is also robust to the natural environments and computationally efficient.

Although supervised deep representation learning has attracted enormous attentions across areas of pattern recognition and computer vision, little progress has been made towards unsupervised deep representation learning for image clustering. In this paper, we propose a deep spectral analysis network for unsupervised representation learning and image clustering. While spectral analysis is established with solid theoretical foundations and has been widely applied to unsupervised data mining, its essential weakness lies in the fact that it is difficult to construct a proper affinity matrix and determine the involving Laplacian matrix for a given dataset. In this paper, we propose a SA-Net to overcome these weaknesses and achieve improved image clustering by extending the spectral analysis procedure into a deep learning framework with multiple layers. The SA-Net has the capability to learn deep representations and reveal deep correlations among data samples. Compared with the existing spectral analysis, the SA-Net achieves two advantages: (i) Given the fact that one spectral analysis procedure can only deal with one subset of the given dataset, our proposed SA-Net elegantly integrates multiple parallel and consecutive spectral analysis procedures together to enable interactive learning across different units towards a coordinated clustering model; (ii) Our SA-Net can identify the local similarities among different images at patch level and hence achieves a higher level of robustness against occlusions. Extensive experiments on a number of popular datasets support that our proposed SA-Net outperforms 11 benchmarks across a number of image clustering applications., Comment: arXiv admin note: text overlap with arXiv:2009.05235

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of dataset-specific CNN architecture, which mostly performed by either experience or expertise is a time-consuming and error-prone process. To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets. The CNN architectures, and recently datasets also, are categorized as deep, shallow, wide, etc. This paper tries to formalize these terms along with answering the following questions. (i) What is the impact of deeper/shallow architectures on the performance of the CNN w.r.t. FC layers?, (ii) How the deeper/wider datasets influence the performance of CNN w.r.t. FC layers?, and (iii) Which kind of architecture (deeper/ shallower) is better suitable for which kind of (deeper/ wider) datasets. To address these findings, we have performed experiments with three CNN architectures having different depths. The experiments are conducted by varying the number of FC layers. We used four widely used datasets including CIFAR-10, CIFAR-100, Tiny ImageNet, and CRCHistoPhenotypes to justify our findings in the context of the image classification problem. The source code of this research is available at https://github.com/shabbeersh/Impact-of-FC-layers., This paper is accepted for publication in Neurocomputing Journal

This paper addresses two issues toward practical use of wearable electroencephalogram (EEG) measurement devices. Ocular (eye movement and blink) artifacts often contaminate EEGs and deteriorate the performance of EEG-based brain–computer interfaces (BCIs). Although wearable consumer-grade EEG devices with single electrode allow users to operate BCIs conveniently in daily lives, it remains a challenging issue to attenuate ocular artifacts from single-channel measurements without spatial information. Existing ocular artifact reduction methods are, however, not simple enough for single-channel EEG data in the sense that they require an additional reference channel and/or pre-processing for artifact segment detection. Another issue is how to assess the performance of artifact reduction; the existing studies have used their own datasets that are not accessible from other researchers. Then, this paper makes two major contributions. (1) This paper proposes a novel ocular artifact reduction method, multi-scale dictionary learning (MSDL), which operates under single-channel measurements and without artifact segment detection. (2) We also develop a semi-simulation setting for quantitative evaluation with a publicly available EEG dataset. In particular, we employed BCI Competition IV Dataset 2a, on which the proposed method was compared with state-of-art methods. The proposed technique showed the best performance for recovering artifact-reduced waveforms from single-channel data compared to the other artifact reduction methods. The Matlab scripts for semi-simulation data generation and single-channel artifact reduction are available on GitHub .

In online-learning, the data is incrementally received and the distributions from which it is drawn may keep changing over time. This phenomenon is widely known as concept drift. Such changes may affect the generalization of a learned model to future data. This problem may be exacerbated by the form of the drift itself changing over time. Quantitative measures to describe and analyze the concept drift have been proposed in previous work. A description composed from these measures is called a concept drift map. We believe that these maps could be useful for guiding how much knowledge in the old model should be forgotten. Therefore, this paper presents an adaptive online learning model that uses a concept drift map to regulate the forgetting factor of an extreme learning machine. Specifically, when a batch of new instances are labeled, the distribution of each class on each attribute is firstly estimated, and then it is compared with the distribution estimated in the previous batch to calculate the magnitude of concept drift, which is further used to regulate the forgetting factor and to update the learning model. Therefore, the novelty of this paper lies in that a quantitative distance metric between two distributions constructed on continuous attribute space is presented to construct concept drift map which can be further associated with the forgetting factor to make the learning model adapt the concept drift. Experimental results on several benchmark stream data sets show the proposed model is generally superior to several previous algorithms when classifying a variety of data streams subject to drift, indicating its effectiveness and feasibility.

Currently, knowledge discovery in databases is an essential first step when identifying valid, novel and useful patterns for decision making. There are many real-world scenarios, such as bankruptcy prediction, option pricing or medical diagnosis, where the classification models to be learned need to fulfill restrictions of monotonicity (i.e. the target class label should not decrease when input attributes values increase). For instance, it is rational to assume that a higher debt ratio of a company should never result in a lower level of bankruptcy risk. Consequently, there is a growing interest from the data mining research community concerning monotonic predictive models. This paper aims to present an overview of the literature in the field, analyzing existing techniques and proposing a taxonomy of the algorithms based on the type of model generated. For each method, we review the quality metrics considered in the evaluation and the different data sets and monotonic problems used in the analysis. In this way, this paper serves as an overview of monotonic classification research in specialized literature and can be used as a functional guide for the field.

Twin Support Vector Machines (TWSVMs) have emerged as an efficient alternative to Support Vector Machines (SVM) for learning from imbalanced datasets. The TWSVM learns two non-parallel classifying hyperplanes by solving a couple of smaller sized problems. However, it is unsuitable for large datasets, as it involves matrix operations. In this paper, we discuss a Twin Neural Network (Twin NN) architecture for learning from large unbalanced datasets. The objective functions of the networks in the Twin NN are designed to realize the idea of the Twin SVM with non-parallel decision boudaries for the respective classes, while also being able to reduce model complexity. The Twin NN optimizes the feature map, allowing for better discrimination between classes. The paper also discusses an extension of the Twin NN for multiclass datasets. This architecture trains as many neural networks as the number of classes, and has the additional advantage that it does not have any hyper-parameter which requires tuning. Results presented in the paper demonstrate that the Twin NN generalizes well and scales well on large unbalanced datasets.

Feature selection is an important step in building classifiers for high-dimensional data problems, such as EEG classification for BCI applications. This paper proposes a new wrapper method for feature selection, based on a multi-objective evolutionary algorithm, where the representation of the individuals or potential solutions, along with the breeding operators and objective functions, have been carefully designed to select a small subset of features that has good generalization capability, trying to avoid the over-fitting problems that wrapper methods usually suffer. A novel feature ranking procedure is also proposed in order to analyze the stability of the proposed wrapper method. Four different classification schemes have been applied within the proposed wrapper method in order to evaluate its accuracy and stability for feature selection on a real motor imagery dataset. Experimental results show that the wrapper method presented in this paper is able to obtain very small subsets of features, which are quite stable and also achieve high classification accuracy, regardless of the classifiers used., Project TIN2015-67020-P (Spanish “Ministerio de Economía y Competitividad”), European Regional Development Funds (ERDF)

It is a big challenge of computer vision to make machine automatically describe the content of an image with a natural language sentence. Previous works have made great progress on this task, but they only use the global or local image feature, which may lose some important subtle or global information of an image. In this paper, we propose a model with 3-gated model which fuses the global and local image features together for the task of image caption generation. The model mainly has three gated structures. 1) Gate for the global image feature, which can adaptively decide when and how much the global image feature should be imported into the sentence generator. 2) The gated recurrent neural network (RNN) is used as the sentence generator. 3) The gated feedback method for stacking RNN is employed to increase the capability of nonlinearity fitting. More specially, the global and local image features are combined together in this paper, which makes full use of the image information. The global image feature is controlled by the first gate and the local image feature is selected by the attention mechanism. With the latter two gates, the relationship between image and text can be well explored, which improves the performance of the language part as well as the multi-modal embedding part. Experimental results show that our proposed method outperforms the state-of-the-art for image caption generation., Comment: 35 pages, 7 figures, magazine

In recent years, convolutional neural networks (CNNs) have shown great performance in various fields such as image classification, pattern recognition, and multi-media compression. Two of the feature properties, local connectivity and weight sharing, can reduce the number of parameters and increase processing speed during training and inference. However, as the dimension of data becomes higher and the CNN architecture becomes more complicated, the end-to-end approach or the combined manner of CNN is computationally intensive, which becomes limitation to CNN’s further implementation. Therefore, it is necessary and urgent to implement CNN in a faster way. In this paper, we first summarize the acceleration methods that contribute to but not limited to CNN by reviewing a broad variety of research papers. We propose a taxonomy in terms of three levels, i.e. structure level, algorithm level, and implementation level, for acceleration methods. We also analyze the acceleration methods in terms of CNN architecture compression, algorithm optimization, and hardware-based improvement. At last, we give a discussion on different perspectives of these acceleration and optimization methods within each level. The discussion shows that the methods in each level still have large exploration space. By incorporating such a wide range of disciplines, we expect to provide a comprehensive reference for researchers who are interested in CNN acceleration.

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified and exponential linear units. As the generalized form, MPELU shares the advantages of Parametric Rectified Linear Unit (PReLU) and Exponential Linear Unit (ELU), leading to better classification performance and convergence property. In addition, weight initialization is very important to train very deep networks. The existing methods laid a solid foundation for networks using rectified linear units but not for exponential linear units. This paper complements the current theory and extends it to the wider range. Specifically, we put forward a way of initialization, enabling training of very deep networks using exponential linear units. Experiments demonstrate that the proposed initialization not only helps the training process but leads to better generalization performance. Finally, utilizing the proposed activation function and initialization, we present a deep MPELU residual architecture that achieves state-of-the-art performance on the CIFAR-10/100 datasets. The code is available at https://github.com/Coldmooon/Code-for-MPELU .

Pedestrian detection and tracking have become an important field in the computer vision research area. This growing interest, started in the last decades, might be explained by the multitude of potential applications that could use the results of this research field, e.g. robotics, entertainment, surveillance, care for the elderly and disabled, and content-based indexing. In this survey paper, vision-based pedestrian detection systems are analysed based on their field of application, acquisition technology, computer vision techniques and classification strategies. Three main application fields have been individuated and discussed: video surveillance, human-machine interaction and analysis. Due to the large variety of acquisition technologies, this paper discusses both the differences between 2D and 3D vision systems, and indoor and outdoor systems. The authors reserved a dedicated section for the analysis of the Deep Learning methodologies, including the Convolutional Neural Networks in pedestrian detection and tracking, considering their recent exploding adoption for such a kind systems. Finally, focusing on the classification point of view, different Machine Learning techniques have been analysed, basing the discussion on the classification performances on different benchmark datasets. The reported results highlight the importance of testing pedestrian detection systems on different datasets to evaluate the robustness of the computed groups of features used as input to classifiers.

Computer simulation, which has been proved to be an effective approach to problem solving, is nowadays widely used in modern science. However, it requires a lot of computing resources, which are difficult for general users to acquire. In this paper, we design a Web based system to implement on-line simulation system for ordinary users. As a useful example, the simulation of one type of collision detection model is presented in this paper. Moreover, the software application of simulation is offered as a service on Web. Meanwhile, the incorporation of general vector machine (GVM, a type of neural network) to intelligently predict the relationship between simulation parameters and computation resources is presented, which could further provide more information for system monitoring and scheduling. The system has demonstrated efficiency and intuitiveness for users of this type of applications.

[EN] This paper presents an approach of a social emotional model, which allows to extract the social emotion of a group of intelligent entities. The emotional model PAD allows to represent the emotion of an intelligent entity in 3-D space, allowing the representation of different emotional states. The social emotional model presented in this paper uses individual emotions of each one of the entities, which are represented in the emotional space PAD. Using a social emotional model within intelligent entities allows the creation of more real simulations, in which emotional states can influence decision-making. The result of this social emotional mode is represented by a series of examples, which are intended to represent a number of situations in which the emotions of each individual modify the emotion of the group. Moreover, the paper introduces an example which employs the proposed model in order to learn and predict future actions trying to influence in the social emotion of a group of people., This work is partially supported by the MINECO/FEDER TIN2015-65515-C4-1-R and the FPI grant AP2013-01276 awarded to Jaime-Andres Rincon.

Dictionary learning has played an important role in the success of sparse representation. Although discriminative synthesis dictionary learning for sparse representation with a high-computational-complexity l0 or l1 norm constraint has been well studied for image classification, jointly and discriminatively learning an analysis dictionary and a synthesis dictionary is still in its infant stage. As a dual of synthesis dictionary, the recently developed analysis dictionary can provide a complementary view of data representation, which can have a much lower time complexity than sparse synthesis representation. Although several class-specific analysis-synthesis dictionary, which may have a big correlation between different classes' dictionaries, have been developed, how to learn a more compact and discriminative universal analysis-synthesis dictionary is still open. In this paper, to provide a more complete view of discriminative data representation, we propose a novel model of discriminative analysis-synthesis dictionary learning (DASDL), in which a linear classifier based on the coding coefficient is jointly learned with the dictionary pair, thus the performance of the classifier and the representational power of the dictionary pair being considered at the same time by the same optimization procedure. The size of the learned dictionaries can be very small since the analysis-synthesis dictionary is shared by all class data. An iterative algorithm to efficiently solve the proposed DASDL is presented in this paper. The experiments on face recognition, gender classification, action recognition and image classification clearly show the superiority of the proposed DASDL.

In today׳s society where audio–visual content is ubiquitous, violence detection in movies and Web videos has become a decisive functionality, e.g., for providing automated youth protection services. In this paper, we concentrate on two important aspects of video content analysis: Time efficiency and modeling of concepts (in this case, violence modeling). Traditional approaches to violent scene detection build on audio or visual features to model violence as a single concept in the feature space. Such modeling does not always provide a faithful representation of violence in terms of audio–visual features, as violence is not necessarily located compactly in the feature space. Consequently, in this paper, we target to close this gap. To this end, we present a solution which uses audio–visual features (MFCC-based audio and advanced motion features) and propose to model violence by means of multiple (sub)concepts. To cope with the heavy computations induced by the use of motion features, we perform a coarse-to-fine analysis, starting with a coarse-level analysis with time efficient audio features and pursuing with a fine-level analysis with advanced features when necessary. The results demonstrate the potential of the proposed approach on the standardized datasets of the latest editions of the MediaEval Affect in Multimedia: Violent Scenes Detection (VSD) task of 2014 and 2015.

© 2016 Elsevier B.V. Gait recognition degrades dramatically when gaits are captured from different directions or at different distances due to the low similarity between the registration and the query. This paper addresses the distance metric learning problem in matching between dual cross-domain gaits. Most existing distance metric learning algorithms are only able to match among a set of single domain gaits, but fail to measure the similarity of cross-domain gaits. Traditional gait recognition faces serious challenges, such as various low resolution images, which is caused by acquisition at different distances or different sampling devices, and various body shapes captured by different direction cameras. This paper presents a novel nonlinear coupled mappings (NCMs) algorithm to successfully match between the cross-domain gaits. The relationships within the training data as nodes in a graph are modeled in the kernel space and the constraint is designed to make the difference minimized between cross-domain gaits for an identical subject. Meanwhile, it makes the cross-domain gaits for different subjects disperse more separately with a large margin by using the supervised similarity matrix. Comprehensive experiments show that the proposed algorithm obtains higher accuracy than state-of-the-art algorithms.

This paper aims to solve the keypoint correspondence problem in lunar surface images, a typical correspondence task under point ambiguity. Point ambiguity may be caused by repetitive patterns, cluttered scenes, and outliers in the images, which makes the local descriptors less discriminative. In this paper we introduce locally affine-invariance constraints on graphs to tackle the keypoint correspondence problem under point ambiguity. The key idea is that each point can be represented with the affine combination of its neighbors. It is suitable for our problem because it is not only invariant to scale and rotational change, but also more resistant to outliers. Specifically, we introduce the locally affine-invariance constraints into the subgraph matching problem and the common subgraph matching problem. The locally affine-invariance constraint is not directly applicable on common subgraph matching due to its dependency on awareness of selected keypoints. This problem is approximately addressed by solving a series of reliable matching identification and rematching problems. In the experiments, we first apply the proposed method on standard graph matching datasets to evaluate its effectiveness on general correspondence problem under point ambiguity, and second validate the applicability on the lunar surface image dataset.

Pedestrians, in videos taken from fixed cameras, tend to appear and disappear at precise locations such as doors, gateways or edges of the scene: we refer to locations where pedestrians appear as sources (potential origins) and the locations where they disappear as sinks (potential destinations). The detection of these points and the characterization of the flows connecting them represent a typical preliminary step in most pedestrian studies and it can be supported by computer vision approaches. In this paper we propose an algorithm in which a scene is overlaid by a grid of particles initializing a dynamical system defined by optical flow, a high level global motion information. Time integration of the dynamical system produces short particle trajectories (tracklets), representing dense but short motion patterns in segments of the scene; tracklets are then extended into longer tracks that are grouped using an unsupervised clustering algorithm, where the similarity is measured by the Longest Common Subsequence. The analysis of these clusters supports the identification of sources and sinks related to a single video segment. Local segment information is finally combined to achieve a global set of traces identifying sources and sinks, and characterizing the flow of pedestrians connecting them. The paper presents the defined technique and it discusses its application in a real-world scenario.

In this paper, we examine the problem of learning sparse representations of visual patterns in the context of artificial and biological vision systems. There are a myriad of strategies for sparse coding that often result in similar feature properties for the learned feature set. Typically this results in a bank of Gabor-like or edge filters that are sensitive to a range of distinct angular and radial frequencies. The theory and experimentation that is presented in this paper serves to provide a better understanding of a number of specific properties related to low-level feature learning. This includes close examination of the role of phase pairing in complex cells, the role of depth information and its relationship to variation of intensity and chroma, and deriving hybrid features that borrow from both analytic forms and statistical methods. Together, these specific examples provide context for more general discussion of effective strategies for feature learning. In particular, we make the case that imposing additional constraints on mechanisms for feature learning inspired by biological vision systems can be useful in guiding constrained optimization towards convergence, or specific desirable computational properties for representation of visual input in artificial vision systems.

From the past few years, the size of the data grows exponentially with respect to volume, velocity, and dimensionality due to wide spread use of embedded and distributed surveillance cameras for security reasons. In this paper, we have proposed an integrated approach for biometric-based image retrieval and processing which addresses the two issues. The first issue is related to the poor visibility of the images produced by the embedded and distributed surveillance cameras, and the second issue is concerned with the effective image retrieval based on the user query. This paper addresses the first issue by proposing an integrated image enhancement approach based on contrast enhancement and colour balancing methods. The contrast enhancement method is used to improve the contrast, while the colour balancing method helps to achieve a balanced colour. Importantly, in the colour balancing method, a new process for colour cast adjustment is introduced which relies on statistical calculation. It adjusts the colour cast and maintains the luminance of the image. The integrated image enhancement approach is applied to the enhancement of low quality images produced by surveillance cameras. The paper addresses the second issue relating to image retrieval by proposing a content-based image retrieval approach. The approach is based on the three features extraction methods namely colour, texture and shape. Colour histogram is used to extract the colour features of an image. Gabor filter is used to extract the texture features and the moment invariant is used to extract the shape features of an image. The use of these three algorithms ensures that the proposed image retrieval approach produces results which are highly relevant to the content of an image query, by taking into account the three distinct features of the image and the similarity metrics based on Euclidean measure. In order to retrieve the most relevant images, the proposed approach also employs a set of fuzzy heuristics to improve the quality of the results further. The results show the proposed approaches perform better than the well-known existing approaches.

Increasing deployment of intermittent power generation from renewable resources in the smart grid, such as photovoltaic (PV) or wind farm, will cause large system frequency fluctuation when the load-frequency control (LFC) capacity is not enough to compensate the unbalance of generation and load demand. Even worse, the system inertia will decrease when the smart grid is in island operating mode, which would degrade system damping and cause system instability. Meanwhile, electric vehicles (EVs) will be widely used by customers in the near future, where the EV station could be treated as dispersed battery energy storage. Therefore, the vehicle-to-grid (V2G) technology can be employed to compensate for inadequate LFC capacity, thus improving the island smart grid frequency stability. In this paper, an on-line reinforcement learning (RL) based method, called goal representation adaptive dynamic programming (GrADP), is employed to adaptive control of units in an island smart grid. In the controller design, adaptive supplementary control signals are provided to proportional-integral-derivative (PID) controller by GrADP in a real-time manner. Comparative simulation studies on a benchmark smart grid with micro-turbine (MT), EVs, PV array and wind power are carried out among the GrADP controller, the original PID controller and the particle swarm optimization (PSO) based fuzzy logic controller. Simulation results demonstrate competitive performance and satisfied learning ability of the GrADP based coordinate controller. Moreover, the impact of signal transmission delay on the control performance is also considered, and suggestions to address this issue are given in the paper.

In this paper, a new hidden layer construction method for Extreme Learning Machines (ELMs) is investigated, aimed at generating a diverse set of weights. The paper proposes two new ELM variants: Binary ELM, with a weight initialization scheme based on { 0 , 1 } -weights; and Ternary ELM, with a weight initialization scheme based on { - 1 , 0 , 1 } -weights. The motivation behind this approach is that these features will be from very different subspaces and therefore each neuron extracts more diverse information from the inputs than neurons with completely random features traditionally used in ELM. Therefore, ideally it should lead to better ELMs. Experiments show that indeed ELMs with ternary weights generally achieve lower test error. Furthermore, the experiments show that the Binary and Ternary ELMs are more robust to irrelevant and noisy variables and are in fact performing implicit variable selection. Finally, since only the weight generation scheme is adapted, the computational time of the ELM is unaffected, and the improved accuracy, added robustness and the implicit variable selection of Binary ELM and Ternary ELM come for free.

The emergence of ubiquitous sources of streaming data has given rise to the popularity of algorithms for online machine learning. In that context, Hoeffding trees represent the state-of-the-art algorithms for online classification. Their popularity stems in large part from their ability to process large quantities of data with a speed that goes beyond the processing power of any other streaming or batch learning algorithm. As a consequence, Hoeffding trees have often been used as base models of many ensemble learning algorithms for online classification. However, despite the existence of many algorithms for online classification, ensemble learning algorithms for online regression do not exist. In particular, the field of online any-time regression analysis seems to have experienced a serious lack of attention. In this paper, we address this issue through a study and an empirical evaluation of a set of online algorithms for regression, which includes the baseline Hoeffding-based regression trees, online option trees, and an online least mean squares filter. We also design, implement and evaluate two novel ensemble learning methods for online regression: online bagging with Hoeffding-based model trees, and an online RandomForest method in which we have used a randomized version of the online model tree learning algorithm as a basic building block. Within the study presented in this paper, we evaluate the proposed algorithms along several dimensions: predictive accuracy and quality of models, time and memory requirements, bias–variance and bias–variance–covariance decomposition of the error, and responsiveness to concept drift.

This paper describes the algorithms used to estimate the state of consumption of a pump based on dynamic pressure or vibrations. To create algorithms, the author used computational intelligence methods in the form of neural networks. In order to perform the analysis, data analysis systems were designed based on three neural networks: multilayer perceptron neural network (MLP), generalized regression neural network (GRNN) and probabilistic neural network (PNN). Processing of the input signal in the final result of the analysis consisted of several steps. First, the measurement data were preprocessed (delete constant component, normalization, standardization, reduction, fast Fourier transform (FFT), etc.), and training and test sets were prepared using the matrices with the expected system answers. The last step was the analysis, consisting of design data analysis systems based on artificial neural networks and their learning and testing. On the basis of the obtained results the effectiveness of neural networks and the methods of pre-processing of the signals applied to approximate the state of consumption of the displacement pump were evaluated. Design systems were evaluated based on accuracy (generated error) and complexity (number of parameters and training time) criteria. The main contribution of the paper is to design and compare methods for pre-processing the signal, and to design and compare the effectiveness of the three neural networks in the diagnosis consumption of a positive displacement pump.

Given several different new product development projects and limited resources, this paper is concerned with the optimal allocation of resources among the projects. This is clearly a multi-objective optimization problem (MOOP), because each new product development project has both a profit expectation and a loss expectation, and such expectations vary according to allocated resources. In such a case, the goal of multi-objective new product development (MONPD) is to maximize the profit expectation while minimizing the loss expectation. As is well known, Pareto optimality and the Pareto front are extremely important to resolve MOOPs. Unlike many other MOOP methods which provide only a single Pareto optimal solution or an approximation of the Pareto front, this paper reports a novel method to calculate the complete Pareto front for the MONPD. Some theoretical conditions and a ripple-spreading algorithm together play a crucial role in finding the complete Pareto front for the MONPD. Simulation results illustrate that the reported method, by calculating the complete Pareto front, can provide the best support to decision makers in the MONPD.

In this paper, an intelligent swarm based-wavelet neural network for affective mobile designed is presented. The contribution on this paper is to develop a new intelligent particle swarm optimization (iPSO), where a fuzzy logic system developed based on human knowledge is proposed to determine the inertia weight for the swarm movement of the PSO and the control parameter of a newly introduced cross-mutated operation. The proposed iPSO is used to optimize the parameters of wavelet neural network. An affective design of mobile phones is used to evaluate the effectiveness of the proposed iPSO. It has been found that significantly better results in a statistical sense can be obtained by the iPSO comparing with the existing hybrid PSO methods.

The advent of the Social Web has enabled anyone with an Internet connection to easily create and share their ideas, opinions and content with millions of other people around the world. In pace with a global deluge of videos from billions of computers, smartphones, tablets, university projectors and security cameras, the amount of multimodal content on the Web has been growing exponentially, and with that comes the need for decoding such information into useful knowledge. In this paper, a multimodal affective data analysis framework is proposed to extract user opinion and emotions from video content. In particular, multiple kernel learning is used to combine visual, audio and textual modalities. The proposed framework outperforms the state-of-the-art model in multimodal sentiment analysis research with a margin of 10–13% and 3–5% accuracy on polarity detection and emotion recognition, respectively. The paper also proposes an extensive study on decision-level fusion.

This paper proposes food image classification methods exploiting both local appearance and global structural information of food objects. The contribution of the paper is threefold. First, non-redundant local binary pattern (NRLBP) is used to describe the local appearance information of food objects. Second, the structural information of food objects is represented by the spatial relationship between interest points and encoded using a shape context descriptor formed from those interest points. Third, we propose two methods of integrating appearance and structural information for the description and classification of food images. We evaluated the proposed methods on two datasets. Experimental results verified that the combination of local appearance and structural features can improve classification performance.

As the simplest extension to linear classifiers, piecewise linear (PWL) classifiers have attracted a lot of attention, because of their simplicity and classification capability. In this paper, a PWL feature mapping is introduced by investigating the property of the PWL classification boundary. Then support vector machines (SVM) with PWL feature mappings are proposed, called PWL-SVMs. In this paper, it is shown that some widely used PWL classifiers, such as k-nearest-neighbor, adaptive boosting of linear classifier and intersection kernel support vector machine, can be represented by the proposed feature mapping. That means the proposed PWL-SVMs at least can achieve the performance of the above PWL classifiers. Moreover, PWL-SVMs enjoy good properties of SVM and the performance on numerical experiments illustrates the effectiveness. Then some extensions are discussed and the application of PWL-SVMs can be expected. © 2013 Elsevier B.V. publisher: Elsevier articletitle: Support vector machines with piecewise linear feature mapping journaltitle: Neurocomputing articlelink: http://dx.doi.org/10.1016/j.neucom.2013.01.023 content_type: article copyright: Copyright © 2013 Elsevier B.V. All rights reserved. ispartof: Neurocomputing vol:117 pages:118-127 status: published

Clustering is used in many applicative fields to summarize information into a small number of groups. Motivated by behavioral extraction issues from urban data, the interest of this paper is to propose a classification method that allows modeling the evolution of cluster profiles over time while considering common regressive effects. The parameters of the proposed model are estimated using variational approximation because maximum likelihood estimation is not suitable in this case. The ability of the model to estimate parameters is evaluated using various simulated data and compared with two other models.

This is the post-print version of the final paper published in Neurocomputing. The published article is available from the link below. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. Copyright @ 2013 Elsevier B.V. Spam, under a variety of shapes and forms, continues to inflict increased damage. Varying approaches including Support Vector Machine (SVM) techniques have been proposed for spam filter training and classification. However, SVM training is a computationally intensive process. This paper presents a MapReduce based parallel SVM algorithm for scalable spam filter training. By distributing, processing and optimizing the subsets of the training data across multiple participating computer nodes, the parallel SVM reduces the training time significantly. Ontology semantics are employed to minimize the impact of accuracy degradation when distributing the training data among a number of SVM classifiers. Experimental results show that ontology based augmentation improves the accuracy level of the parallel SVM beyond the original sequential counterpart.

In this paper, we propose a system for face identification. Given two query face images, our task is to tell whether or not they are of the same person. The main contribution of this paper comes from two aspects: (1) We adopt the one-shot similarity kernel [35] for learning the similarity of two face images. The learned similarity measures are then used to map a face image to reference images. (2) We propose a graph-based method for selecting an optimal set of reference images. Instead of directly working on the image features, we use the learned similarity to the reference images as the new features and compute the corresponding matching score of the two query images. Our approach is effective and easy to implement. We show encouraging and favorable results on the ''Labeled Faces in the Wild'' - a challenging data set of faces.

This paper studies the problem of expertise matching with various constraints. Expertise matching, which aims to find the alignment between experts and queries, is a common problem in many applications such as conference paper-reviewer assignment, product-reviewer alignment, and product-endorser matching. Most existing methods formalize this problem as an information-retrieval problem and focus on finding a set of experts for each query independently. However, in real-world systems, various constraints are often needed to be considered. For example, in order to review a paper, it is desirable that there is at least one senior reviewer to guide the reviewing process. An important question is: ''Can we design a framework to efficiently find the optimal solution for expertise matching under various constraints?'' This paper explores such an approach by formulating the expertise matching problem in a constraint-based optimization framework. In the proposed framework, the problem of expertise matching is linked to a convex cost flow problem, which guarantees an optimal solution under various constraints. We also present an online matching algorithm to support incorporating user feedbacks in real time. The proposed approach has been evaluated on two different genres of expertise matching problems, namely conference paper-reviewer assignment and teacher-course assignment. Experimental results validate the effectiveness of the proposed approach. Based on the proposed method, we have also developed an online system for paper-reviewer suggestions, which has been used for paper-reviewer assignment in a top conference and feedbacks from the conference organizers are very positive.

Despite many decades of research on high-performance Deep Neural Network (DNN) accelerators, their massive computational demand still requires resource-efficient, optimized and parallel architecture for computational acceleration. Contemporary hardware implementations of DNNs face the burden of excess area requirement due to resource-intensive elements such as multipliers and non-linear Activation Functions (AFs). This paper proposes DNN with reused hardware-costly AF by multiplexing data using shift-register. The on-chip quantized log 2 based memory addressing with an optimized technique is used to access input features, weights, and biases. This way the external memory bandwidth requirement is reduced and dynamically adjusted for DNNs. Further, high-throughput and resource-efficient memory elements for sigmoid activation function are extracted using the Taylor series and its order expansion have been tuned for better test accuracy. The performance is validated and compared with previous work for the MNIST dataset. Besides, the digital design of AF is synthesized at 45 nm technology node and physical parameters are compared with previous work. The proposed hardware reused architecture is verified for neural network 16:16:10:4 using 8-bit dynamic fixed-point arithmetic and implemented on Xilinx Zynq xc7z010clg400 SoC using 100 MHz clock. The implemented architecture uses 25% less hardware resources and consumes 12% less power without performance loss, compared to other state-of-the-art implementations, as lower hardware resources and power consumption are especially important for increasingly important edge computing solutions.

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions. Submitted/Accepted version

The problem of residual variance estimation consists of estimating the best possible generalization error obtainable by any model based on a finite sample of data. Even though it is a natural generalization of linear correlation, residual variance estimation in its general form has attracted relatively little attention in machine learning. In this paper, we examine four different residual variance estimators and analyze their properties both theoretically and experimentally to understand better their applicability in machine learning problems. The theoretical treatment differs from previous work by being based on a general formulation of the problem covering also heteroscedastic noise in contrary to previous work, which concentrates on homoscedastic and additive noise. In the second part of the paper, we demonstrate practical applications in input and model structure selection. The experimental results show that using residual variance estimators in these tasks gives good results often with a reduced computational complexity, while the nearest neighbor estimators are simple and easy to implement.

This paper presents an ensemble neural network and interval neutrosophic sets approach to the problem of binary classification. A bagging technique is applied to an ensemble of pairs of neural networks created to predict degree of truth membership, indeterminacy membership, and false membership values in the interval neutrosophic sets. In our approach, the error and vagueness are quantified in the classification process as well. A number of aggregation techniques are proposed in this paper. We applied our techniques to the classical benchmark problems including ionosphere, pima-Indians diabetes, and liver-disorders from the UCI machine learning repository. Our approaches improve the classification performance as compared to the existing techniques which applied only to the truth membership values. Furthermore, the proposed ensemble techniques also provide better results than those obtained from only a single pair of neural networks.