Search

This paper proposes ELMOEA/D, a surrogate-assisted MOEA, for solving costly multi-objective problems in small evaluation budgets. The proposed approach encompasses a state-of-the-art MOEA based on decomposition and Differential Evolution (MOEA/D-DE) assisted by Extreme Learning Machines (ELMs). ELMOEA/D is tested in instances from three well-known benchmarks (ZDT, DTLZ and WFG) with 5-60 decision variables, 2 and 5 objectives. The ELMOEA/D's performance is also analyzed on a real problem (Airfoil Shape Optimization). The impact of some ELMs parameters and an automatic model selection mechanism is investigated. The results obtained by ELMOEA/D are compared with those of two state-of-the-art surrogate approaches (MOEA/D-RBF and ParEGO) and a non-surrogate-based MOEA (MOEA/D). The ELMOEA/D variants are among the best results for most benchmark instances and for the real problem. HighlightsThe problem of solving expensive MOPs with small evaluation budgets is treated.The paper investigates the use of ELM as a surrogate model in MOEAs.A procedure is used to automatically select ELM parameters.The scalability of surrogates concerning the total of decision variables and number of objectives is evaluated.Experimental results show the good performance of ELMOEA/D in different problems.

In this paper, cluster synchronization problem is investigated for a kind of complex dynamical networks with Lurie-type non-linear dynamics. With the aid of a local update law, a pinning adaptive control strategy is proposed to solve the cluster synchronization problem of the networks. Some simple criteria for cluster synchronization are presented for the networks with external disturbances and time delays. Firstly, sufficient conditions are established to realize cluster synchronization of the networks without disturbances and delays. Then, the cluster synchronization problem of the networks with external disturbances is considered. Finally, the cluster synchronization in the networks with time-varying delays is further studied. Numerical examples are given to verify and illustrate the theoretical results. HighlightsThe cluster synchronization in networks with disturbances and delays is studied.An adaptive control strategy is presented for the networks with Lurie-type dynamics.The results in this paper do not require the global information of the networks.

Due to the relay ability of sensory information and communication between cortical regions, the thalamocortical (TC) relay neuron plays an essential role in the therapy of Parkinson's disease. This paper first explores a series of efficient methods for the hardware implementation of TC relay neuron models, aiming to reproduce relevant biological behaviors and present appropriate feedback control in neural dynamics in thalamic systems. In addition, a modified two-dimensional TC neuron model is presented for convenient realization to decrease the complexity of the original model and promote the feasibility of the digital design, which shows significance for the large-scale network simulation of TC-based networks and the establishment of digital thalamus. A system-on-a-chip model-based control system is implemented on an FPGA using the modified TC neuron model, which is aimed at the real-time feedback control of tremor dominant Parkinsonian state. In this paper, the hardware syntheses and theoretical researches are given to illustrate the outstanding performance of the presented hardware implementation. The presented platform can be applied in both the brain-machine interface and the robotic control projects, and the proposed modular hardware framework can be extended to the real-time closed-loop treatments of other dyskinesia diseases. We first present efficient digital implementation of thalamocortical neuron model.Modified thalamocortical neuron model is proposed for a convenient implementation.This model can decrease the resource cost while retaining the biological dynamics.A digital thalamocortical model-based controller is designed using the modified model.The control platform can be applied in real-time control of Parkinson's disease.

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.

Facial expression-based emotion recognition has attracted lots of attention. Higher accurate performance could be expected with help of the other cues, e.g. physiological signals, for some specific blue such as 'Poker Face' and the lack of facial expression. In this paper, physiological signals are utilized for inferring user's emotion. However, the results of physiological-based emotion recognition are still inaccurate in the user-independent scenario since most existing methods ignore the difference in individual response pattern. To this end, we propose a Group-Based IRS (Individual Response Specificity) model to improve performance of physiological-based emotion recognition by taking user's IRS into account. The main contributions of this paper are two-fold: (1) an affective physiological database is collected to analyze human's emotional response pattern. The physiological signals are recorded from 30 subjects in four induced emotions (neutral, sadness, fear and pleasure). Three-channel bio-sensors are used to measure users electrocardiogram (ECG), galvanic skin response (GSR) and photo plethysmography (PPG). (2) In the experiment, the Group-based IRS model is proposed for emotion recognition in user-independent scenario, the effectiveness of which has been validated on our database. The results show that the Group-based IRS model can achieve higher recognition precision than the general model. HighlightsWe collect affective physiological dataset under four induced emotions.The theory of IRS is adopted to build a recognition model.We analyze and discuss the robustness and applicability of physiological signals.The Group-Based IRS model is utilized to improve performance of emotion recognition.

Large scale systems (LSS) have a large size with several control loops. It is always demanding that all the local controllers of the LSS work in an optimal situation to raise the efficiency of the system. Therefore the performance monitoring of the distributed systems is common to detect any roots of deficiency in the subsystems. This paper presents control performance assessment (CPA) for the Rhine-Meuse Delta water network. The Delta water system consists of many rivers and sea outlets with barriers and sluices. The water network is in the low-lying area surrounded by rivers and the North Sea, and because of its location, the system is at high risk of floods. For the monitoring of the system, two new data driven performance indexes based on wavelet-based probability density function (PDF) are designed for the system to assess the performance of the subsystems and also the whole system. Finally, a comparison with Model predictive control benchmark is made to show the capability of the new benchmark. Simulation results show the effectiveness of the suggested methods in detecting the floods. The Rhine-Meuse Delta water network is a large scale system.This paper presents control performance assessment for the Rhine-Meuse Delta water network.Two new data driven performance indexes are considered for monitoring the system.The performance indexes are designed based on wavelet-based probability density function.Simulation results show the ability of the suggested methods in detecting the floods.

This paper investigates the problem of position tracking for the servo system consisting of a permanent magnet synchronous motor and a ball screw. The objective is to design a suitable robust controller, guaranteeing the servo system can track object position smoothly without error. The method proposed in this paper is based on the vector control principle of a alternating current motor combined with mechanics laws of a ball screw and a new relative dynamic model is developed; then a robust position tracking control problem is formulated. By the Lyapunov approach, the existence conditions for a admissible controller are formulated employing convex optimization approach, and the controller design is cast into a asymptotically stable problem subject to several constraints. With the obtained controller, the position tracking problem can be completed with anticipant transient and stable performance. An illustrative example is provided to show the effectiveness of the proposed controller design method.

This paper proposes an online tracking algorithm that employs a confidence combinatorial map model. Drifting is a problem that easily occurs in object tracking and most of the recent tracking algorithms have attempted to solve this problem. In this paper, we propose a confidence combinatorial map that describes the structure of the object, based on which the confidence combinatorial map model is developed. The model associates the relationship between the object in the current frame and that in the previous frame. On the strength of this relationship, more precisely classified samples can be selected and are employed in the model update stage, which directly influences the occurrence of the tracking drift. The proposed algorithm was estimated on several public video sequences and the performance was compared with several state-of-the-art algorithms. The experiments demonstrate that the proposed algorithm outperforms other comparative algorithms and gives a very good performance.

At the moment, smell sensors for odor source localization in mobile robotics represent a topic of interest for researchers around the world. In particular, we introduce in this paper the idea of developing biologically inspired sniffing robots in combination with bioinspired techniques such as evolutionary computing. The aim is to approach the problem of creating an artificial nose that can be incorporated into a real working system, while considering the environmental model and odor behavior, the perception system, and algorithm for tracking the odor plume. Current algorithms try to emulate animal behavior in an attempt to replicate their capability to follow odors. Nevertheless, odor perception systems are still in their infancy and far from their biological counterpart. This paper presents a proposal in which a real-working artificial nose is tested as a perception system within a mobile robot. Genetic programming is used as the learning technique platform to develop odor source localization algorithms. Experiments in simulation and with an actual working robot are presented and the results compared with two algorithms. The quality of results demonstrates that genetic programming is able to recreate chemotaxis behavior by considering mathematical models for odor propagation and perception system.

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.

The Bag-of-Visual-Words (BoVW) representation has been widely used to approach a number of different high-level computer vision tasks. The idea behind the BoVW representation is similar to the Bag-of-Words (BoW) used in Natural Language Processing (NLP) tasks: to extract features from the dataset, then build feature histograms that represent each instance. Although the approach is simple and effective facilitating its applicability to a wide range of problems, it inherits a well-known limitation from the traditional BoW; the disregarding of spatial information among extracted features (sequential information in text), which could be useful to capture discriminative visual-patterns. In this paper, we alleviate this limitation with the joint use of visual words and multi-directional sequences of visual words (visual n-grams). The contribution of this paper is twofold: (i) to build new simple-effective visual features inspired in the popular idea of n-gram representations in NLP and (ii) to propose the Multiple Kernel Learning (MKL) strategies to better exploit the joint use of visual words and visual n-grams in Image Classification (IC) tasks. For the former, we propose building a codebook of visual n-grams, and use them as attributes to represent images by means of the BoVW representation. For the second point, we consider the visual words and visual n-grams as different feature spaces, then we propose MKL strategies to better integrate the visual information. We evaluate our proposal in the image classification task using five different datasets: Histopathology, Birds, Butterflies, Scenes and a subset of 6 classes of CalTech-101. Experimental results show that the proposed strategies exploiting our visual n-grams, outperforms or is competitive with (i) the traditional BoVW, (ii) the BoVW using visual n-grams under traditional fusion schemes (e.g., ensemble based classifiers) and (iii) other approaches in the literature for IC that consider the spatial context.

This paper addresses region aggregation issues of multi-agent networks (MANs) that consist of finite number of isolated sub-multi-agent systems (sub-MASs) with multiple equilibria (ME) in multi-dimensional coordinate systems (MDCSs). To investigate aggregation of this kind of MANs via switching strategies, switched systems with ME are used to describe such networks under the case that each agent has a unique equilibrium point and all the equilibria are different from each other. Based on the novel stability concepts of region stability (RS) and exponential region stability (ERS) introduced, this paper proposes several RS and ERS results for sub-MASs with ME via the maximum energy function method, and then presents several region aggregation results for such MANs under three suitable assumptions. Also, a numerical example illustrates the effectiveness and practicality of our new results.

The privacy-preserving data analysis has been gained significant interest across several research communities. The current researches mainly focus on privacy-preserving classification and regression. On the other hand, feature selection is also one of the key problems in data mining and machine learning. However, for privacy-preserving feature selection, the relevant papers are few. In this paper, a local learning-based feature weighting framework is introduced. Moreover, in order to preserve the data privacy during local learning-based feature selection, the objective perturbation and output perturbation strategies are used to produce local learning-based feature selection algorithms with privacy preservation. Meanwhile, we give deep analysis about their privacy preserving property based on the differential privacy model. Some experiments are conducted on benchmark data sets. The experimental results show that our algorithms can preserve the data privacy to some extent and the objective perturbation always obtains higher classification performance than output perturbation when the privacy preserving degree is constant.

Automated seizure detection using EEG has gained increasing attraction in recent years and appeared more and more helpful in both diagnosis and treatment. How to design an appropriate feature extraction method and how to select an efficient classifier are recognized to be crucial in the successful realization. This paper first proposes a new Mahalanobis-similarity-based feature extraction method on the basis of the Mahalanobis distance and discrete wavelet transformation (DWT). Then in order to further improve the performance, this paper designs a fusion feature (MS-SE-FF) in the feature-fusion level, where the Mahalanobis-similarity-based feature characterizing the similarity between signals and the sample-entropy-based feature characterizing the complexity of signals are combined together. Finally, an automated seizure detection method FF-ELM-SD has been built, which is integrated between the novel fusion feature MS-SE-FF and extreme learning machine (ELM). Experimental results demonstrate that the proposed method FF-ELM-SD does a good job in the epileptic seizure detection while preserving the efficiency and simplicity.

The increasing demand for copyright protection has brought extensive interest in video fingerprinting technology, which is considered as an effective way for digital content authentication. In this paper, an innovative method for video authenticity based on the fingerprint of scene frame has been proposed. Since the probability of 5 identical scene frames existing successively in different videos is extremely low, the proposed method firstly extract 5 successive different scene frames to make up the video fingerprint. This video fingerprint is then combined with the ID information of video to form meta fingerprint data. The metadata is stored in Bag-words format, leading to the saving of 75% storage space. In the process of authentication, a binary search of inverted file is applied to accelerate the matching speed. The results of simulation experiments using MATLAB show that the video authenticity method proposed in this paper achieves excellent detection performance, with the average accuracy over 98% at an average speed of 12s per video. This makes the real-time detection become possible on the Internet.

This paper concerns the use of multiple views of a feature set to select a small amount of useful unlabeled data. In the semi-supervised learning (SSL) approach, using a selection strategy, strongly discriminative examples are first selected from unlabeled data and then, together with labeled data, utilized for training a (supervised) classifier or used for re-training the ensemble classifier. In this scenario, the selection strategy plays an important role in improving classification performance. This paper investigates a new selection strategy for a case in which the data are composed of different multiple views: first, multiple views of the data are derived independently; second, each of the views are used to measure corresponding confidence levels with which examples to be selected are evaluated; third, all the confidence levels measured from the multiple views are used as a weighted average to derive the target confidence; this select-and-train process is repeated for a pre-defined number of iterations. The experimental results, obtained using semi-supervised support vector machines for synthetic and real-life benchmark data, demonstrate that the proposed mechanism can compensate for the shortcomings of traditional strategies. In particular, the results demonstrate that when the data is appropriately decomposed into multiple views, this strategy can achieve further improved results in terms of the classification accuracy. HighlightsA small amount of unlabeled data was selected to enhance classification accuracy.To select them efficiently, multiple views of the labeled and unlabeled data were utilized.The confidence levels of the multiple views are referred to derive the target confidence.Run-time characteristics and error rates of the proposed criterion were empirically evaluated.

This paper contributes to the understanding and implementation of different types of locomotion in a snake-like robot by using a proposed unified neural oscillator model as central pattern generator (CPG). A neural oscillator network is suggested so that several rhythmic movements can be generated in order to mimic the actual snake movements on land. The unified coupled neural oscillators in the network provide the desired orientation and displacement for the snake-like robot and they are applied to the different types of snake locomotion by just altering some of the parameters proposed in the paper. The design of snake-like robot, consisting of a series of wheeled links (links with active wheels) connected with each other using the passive prismatic and revolute joints, is also suggested in the paper. The passive prismatic joints facilitate the change of lengths of wheel-less links and in this way the robot can be elongated as well as shortened. In this paper the serpentine, rectilinear, and concertina types of actual snake locomotion are realized, through simulation studies, by using the unified neural oscillator model proposed for the snake-like robots.

This paper investigates function projective synchronization (FPS) of complex dynamical networks (CDNs) with or without external disturbances using error feedback control scheme. The proposed error feedback control scheme contains only error terms, which is quite simple and easy to implement in practical applications. Then, an adaptive error feedback control scheme is designed to achieve FPS in CDNs with or without external disturbances, in which feedback gains can be automatically adapted to suitable constants. Moreover, there is no need to know the norm-bounded of the disturbances. Numerical examples are provided to show the effectiveness of proposed methods. HighlightsThis paper investigates the function projective synchronization (FPS) in complex dynamical networks (CDNs) without or with external disturbances.An error feedback control scheme is proposed for FPS in CDNs. The proposed scheme contains only error terms and is quite simple and easy to implement in practical applications.An adaptive error feedback scheme is designed. The feedback gains can be automatically adapted to suitable constants.The proposed adaptive scheme is shown to be robust to limited accuracy of data and effects of external disturbances.There is no need to know the norm-bounded of the disturbances.

In this paper, the quasi-synchronization of nonlinear coupled networks in the presence of parameter mismatches with time delay via aperiodically intermittent pinning control is investigated. There are two main differences of this paper with previous works: one is that the intermittent pinning control is aperiodic while that in previous works is periodic; the other is that the model is generalized from master-slave coupled systems of only two nodes to general nonlinear coupled networks. By using the aperiodically intermittent pinning control technique, a simple controller to pin the coupled networks to achieve quasi-synchronization is designed. Some sufficient criteria are obtained to guarantee global quasi-synchronization. Moreover, an adaptive algorithm for the control strength is also proposed to realize the quasi-synchronization. Finally, numerical simulations are given to show the validity of our theoretical results.

In this paper, we discuss the long-term time series forecasting using a Multilayer Neural Network with Multi-Valued Neurons (MLMVN). This is a complex-valued neural network with a derivative-free backpropagation learning algorithm. We evaluate the proposed approach using a real-world data set describing the dynamic behavior of an oilfield asset located in the coastal swamps of the Gulf of Mexico. We show that MLMVN can be efficiently applied to univariate and multivariate one-step- and multi-step ahead prediction of reservoir dynamics. This paper is not only intended for proposing to use a complex-valued neural network for forecasting, but to deeper study some important aspects of the application of ANN models to time series forecasting that could be of the particular interest for pattern recognition community. A long-term forecasting of oil production was done using MLMVN.Univariate and multivariate forecasting models were developed.MLMVN is efficient for both multivariate and univariate forecasting models.MLMVN-based prediction combines both regression and pattern recognition approaches.

In this paper, a novel adaptive neural control methodology is addressed for a flexible air-breathing hypersonic vehicle (FAHV) by a fusion of improved back-stepping and a minimal-learning-parameter (MLP) scheme. To facilitate the control design, the vehicle dynamics is decomposed into the altitude subsystem and the velocity subsystem. Different from the traditional back-stepping design, in this paper, the virtual control laws for the altitude dynamics are artificial intermediate variables required only for analytic purpose while only the final actual controller is needed to be implemented. For each subsystem, only one neural network is employed to approximate the lumped uncertainty. Moreover, by the merit of the MLP technique, only one learning parameter is required for neural approximation in each subsystem. The novel contribution with respect to the existing literatures is that the proposed control strategy is concise and the computational load is low. Finally, the effectiveness of the exploited control approach is verified by simulation results in the presence of uncertain parameters.

Clustering ensemble is an important part of ensemble learning. It aims to study and integrate multiple clustering results from different clustering algorithms or same algorithm with different initial parameters for the same dataset. CHAMELEON is a hierarchical clustering algorithm which can discover natural clusters of different shapes and sizes as the result of its merging decision dynamically adapts to the different clustering model characterized. Inspired by the idea of CHAMELEON, the paper proposes a novel clustering ensemble models including semi-supervised method and discusses its application in fault diagnosis of high speed train (HST) running gear. The contributions of this paper include: constructing a sparse graph via the similarity matrix which aggregates multiple clustering results; partitioning the sparse graph (vertex=object, edge weight=similarity) into a large number of relatively small sub-clusters; obtaining the final clustering partition by merging these sub-clusters repeatedly. The experimental results demonstrate that our method outperforms some of state-of-the-art ensemble algorithms regarding the accuracy and stability and recognizes fault patterns of HST running gear effectively.

The prohibitive computational complexity caused by redundant dictionary which is used in signal sparse decomposition has always been perplexing researchers of signal processing all the time. However, large over-complete dictionaries are essential to approximate the signal. In this paper, a decomposition algorithm based on modulation correlation partition (PBMC) is introduced, which improves the process of searching matched atoms in the redundant dictionary of functions. Through analyzing the structure of signals, we unite the frequency factor and phase factor to obtain the 2D modulation factor. The over-complete dictionary is partitioned into several sub-dictionaries according to the modulation correlation of atoms. Each sub-dictionary is represented by a single selected atom which is used in the greedy algorithm. At the end of this paper, experimental results show that the computational complexity of signal sparse decomposition can be adequately reduced by partitioning over-complete dictionary without impacting the decomposition result. HighlightsAn algorithm that raises efficiency of matching pursuit is proposed.Partition strategy is introduced to improve structure of redundant dictionary.The proposed approach is more effective than the traditional ones and has robustness.

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.

A huge number of videos are posted every day on social media platforms such as Facebook and YouTube. This makes the Internet an unlimited source of information. In the coming decades, coping with such information and mining useful knowledge from it will be an increasingly difficult task. In this paper, we propose a novel methodology for multimodal sentiment analysis, which consists in harvesting sentiments from Web videos by demonstrating a model that uses audio, visual and textual modalities as sources of information. We used both feature- and decision-level fusion methods to merge affective information extracted from multiple modalities. A thorough comparison with existing works in this area is carried out throughout the paper, which demonstrates the novelty of our approach. Preliminary comparative experiments with the YouTube dataset show that the proposed multimodal system achieves an accuracy of nearly 80%, outperforming all state-of-the-art systems by more than 20%.

In this paper, an adaptive predictive control algorithm is employed to controlling a class of continuous stirred tank reactor (CSTR) system. The main contribute of this paper is that the CSTR system are in discrete-time form and non-symmetric dead-zone inputs are considered here. The design parameters of control algorithm for the CSTR systems are not so much than before, such that the calculated amount of the control algorithm is less than before. By considering the Radial basis function neural networks (RBFNN), the unknown functions are approximated, the mean value theorem is utilized in the algorithm design process. Based on the Lyapunov analysis method, and choosing the design parameters appropriately, all the signals in the closed-loop system are proved to be semi-global uniformly ultimately bounded (SGUUB) and the tracking error is converged to a small compact set. A simulation example for CSTR systems is studied to demonstrate the effectiveness of the proposed approach.

As a classical partitional clustering algorithm, k-means algorithm is sensitive to initial centroids and may malfunction when dealing with datasets which contain clusters with different scales and densities. To improve the effectiveness of k-means algorithm, an outlier factor based partitional clustering analysis method is presented in this paper. Outlier factor is usually used to indicate the degree of an object to be abnormal in the dataset. For the proposed method, it is used to find the core objects. And then the Must-link constraints is generated to put the neighboring core objects into the same cluster. First, a similar-density-array-based outlier factor is proposed to find the core objects in the dataset. Then the neighboring core objects are distributed into the same sub-cluster. The sub-clusters are treated as the representative objects and these representative objects are then clustered following the process of the traditional k-means algorithm. Finally, the non-core objects are assigned to their nearest clusters, respectively. The experiments are performed on four datasets from UCI Machine Learning Repository and a field dataset from a ball mill pulverizing system. The experimental results verify that the effectiveness of our algorithm is high. HighlightsNew method to combine outlier factor with k-means algorithm, and local information is effectively used.The proposed method is compared with two classical constrained k-means algorithms.Besides UCI datasets, a field dataset from a ball mill pulverizing system is used in the experiment.An outlier factor is proposed in the paper and is compared with LOF and COF in the experiment.The impact of the parameter of the outlier factors are tested and discussed in detail in the experiment.

In this paper, we propose a virtual reality (VR) platform as a case study of machine learning, in this case applied to the goal representation heuristic dynamic programming (GrHDP) approach. In general, a VR platform normally includes a physical module, a control/learning module, and a VR module. It facilitates machine learning research, where scientists and engineers can participate in the simulation process to analyze dynamic experiments. The internal structure of the VR platform can be replaced according to different research targets, so the platform can be extended to other applications. In this paper, we present the detailed VR design strategy, with a number of applications, including a triple-link inverted pendulum balancing problem, a maze navigation problem, and a robot navigation with obstacle avoidance.

Probabilistic K-nearest neighbour (PKNN) classification has been introduced to improve the performance of the original K-nearest neighbour (KNN) classification algorithm by explicitly modelling uncertainty in the classification of each feature vector. However, an issue common to both KNN and PKNN is to select the optimal number of neighbours, K. The contribution of this paper is to incorporate the uncertainty in K into the decision making, and consequently to provide improved classification with Bayesian model averaging. Indeed the problem of assessing the uncertainty in K can be viewed as one of statistical model selection which is one of the most important technical issues in the statistics and machine learning domain. In this paper, we develop a new functional approximation algorithm to reconstruct the density of the model (order) without relying on time consuming Monte Carlo simulations. In addition, the algorithms avoid cross validation by adopting Bayesian framework. The performance of the proposed approaches is evaluated on several real experimental datasets. HighlightsIt finds the optimal number of neighbours K for probabilistic KNN (PKNN).It reconstructs the density of K for the PKNN.It incorporates the uncertainty in K into the decision making.It provides improved PKNN classification using Bayesian model averaging.

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.

Many real-life problems involve dealing with multiple objectives. For example, in network routing the criteria may consist of energy consumption, latency, and channel capacity, which are in essence conflicting objectives. As in many problems there may be multiple (conflicting) objectives, there usually does not exist a single optimal solution. In those cases, it is desirable to obtain a set of trade-off solutions between the objectives. This problem has in the last decade also gained the attention of many researchers in the field of reinforcement learning (RL). RL addresses sequential decision problems in initially (possibly) unknown stochastic environments. The goal is the maximization of the agent's reward in an environment that is not always completely observable. The purpose of this special issue is to obtain a broader picture on the algorithmic techniques at the confluence between multi-objective optimization and reinforcement learning. The growing interest in multi-objective reinforcement learning (MORL) was reflected in the quantity and quality of submissions received for this special issue. After a rigorous review process, seven papers were accepted for publication, and they reflect the diversity of research being carried out within this emerging field of research. The accepted papers consider many different aspects of algorithmic design and the evaluation and this editorial puts them in a unified framework.

In this paper, we propose a novel gender classification framework, which utilizes not only facial features, but also external information, i.e. hair and clothing. Instead of using the whole face, we consider five facial components: forehead, eyes, nose, mouth and chin. We also design feature extraction methods for hair and clothing; these features have seldom been used in previous work because of their large variability. For each type of feature, we train a single support vector machine classifier with probabilistic output. The outputs of these classifiers are combined using various strategies, namely fuzzy integral, maximal, sum, voting, and product rule. The major contributions of this paper are (1) investigating the gender discriminative ability of clothing information; (2) using facial components instead of the whole face to obtain higher robustness for occlusions and noise; (3) exploiting hair and clothing information to facilitate gender classification. Experimental results show that our proposed framework improves classification accuracy, even when images contain occlusions, noise, and illumination changes.

Machine Learning has emerged in the last years as the main solution to many of nowadays’ data-based decision problems. However, while new and more powerful algorithms and the increasing availability of computational resources contributed to a widespread use of Machine Learning, significant challenges still remain. Two of the most significant nowadays are the need to explain a model’s predictions, and the significant costs of training and re-training models, especially with large datasets or in streaming scenarios. In this paper we address both issues by proposing an approach we deem predictive and user-centric. It is predictive in the sense that it estimates the benefit of re-training a model with new data, and it is user-centric in the sense that it implements an explainable interface that produces interpretable explanations that accompany predictions. The former allows to reduce necessary resources (e.g. time, costs) spent on retraining models when no improvements are expected, while the latter allows for human users to have additional information to support decision-making. We validate the proposed approach with a group of public datasets and present a real application scenario.

With intrinsic non-uniform illumination variations in laparoscopic images, such images often suffer from insufficient lighting and low visibility. This in turn may cause incorrect targeting, surgical risk, and extended operating time during laparoscopic surgery. Although various methods for nature image enhancement have been proposed in past decades, surgical laparoscopic image enhancement still needs improving due to issues including naturalness, blurred texture, color cast, and extensive computational time. To address these problems, this paper proposes a distributed Retinex optimization method for laparoscopic image enhancement using refined information fusion. The proposed method minimizes a distributed optimization model with l 2 -norm regularization terms, resulting in a low computational complexity. By integrating the refined image information into the optimization process, our method significantly enhances dark regions while preserving naturalness and texture structures. Experimental results show that our optimization algorithm is more effective than conventional enhancement algorithms in terms of vision augmentation, performance index, and computation time.

The prognostics and health management (PHM) aims to provide a comprehensive solution for equipment health care. Classifying the operation mode of excavator, one of the tasks in the PHM, is important to evaluate the remaining useful lifetime. Several studies have been conducted to classify the operations with either video or sensor data, but they have several limitations to use only one type of data. A model trained with sensor data cannot classify the similar operations such as “digging” and “ditch digging”, whereas a model with video data is vulnerable to surrounding condition like weather. In this paper, to overcome these shortcomings, we propose a deep neural network ensemble called FusionNet that classifies the operations of excavator. Two models are trained with sensor data and video frames respectively, where the feature extractors are transferred to the FusionNet. The proposed network ensemble performs a flexible and well-optimized classification by automatically calculating weights according to the extracted feature vectors and combining them. To verify the proposed model, several experiments are conducted with the real-world data. The proposed model achieves the accuracy of 99.17% which outperforms the conventional methods. We also confirm that the proposed model can address the shortcomings of using only one type of data and maximize the benefits through the automatic weighting of extracted features.

Recently, the Extreme Learning Machine (ELM) algorithm has been applied to various fields due to its rapidity and significant generalization performance. Traditionally, deep learning (DL) and wavelet neural networks (WNN) methods reach a high classification accuracy in machine learning applications. As a result, a new structure based on WNN, deep architecture and ELM is proposed in this paper. The proposed method is based on Extreme Learning Machine Auto-Encoder with DL structure and a composite wavelet activation function used in the hidden nodes. To evaluate the performance of our approach, we used standard benchmark data-sets, namely COIL-20, Pima Indian Diabetes (PID), MNIST and EMNIST. Experimental results show that our method offers satisfactory results and performance compared to other approaches.

Automatic International Classification of Diseases (ICD) coding is an important task in the future of artificial intelligence healthcare. In recent years, a lot of traditional machine learning-based methods have been proposed, and they achieved good results on this task. However, these traditional machine learning-based methods for automatic ICD coding only focus on the semantic features of clinical notes and ignore the feature extraction of ICD titles that are the descriptions of ICD codes. In this paper, we propose a knowledge attention-based deep learning framework called KAICD for automatic ICD coding. KAICD makes full use of the clinic notes and the ICD titles. The semantic features of clinic notes are extracted by a multi-scale convolutional neural network. For ICD titles, we use attention-based Bidirectional Gated Recurrent Unit (Bi-GRU) to build a knowledge database, which can offer additional information. Depending on input clinic notes, we can use the attention mechanism to obtain different knowledge vectors from the knowledge database where some ICD titles are more relevant to the input clinic notes. Last, we concatenate the knowledge vectors and the semantic features of clinic notes, and use them for the final prediction. KAICD is tested on a public dataset Medical Information Mart for Intensive Care III (MIMIC III); it achieves micro-precision of 0.502, micro-recall of 0.428, and micro-f1 of 0.462, which outperforms other competing methods. Furthermore, the results of the ablation study show that the knowledge database of ICD titles learned by the attention-based Bi-GRU enhances the feature expression and improves the prediction performance.

Meta-learning aims to leverage experience from previous tasks to achieve an effective and fast adaptation ability when encountering new tasks. However, it is unclear how the generalization property applies to new tasks. Probably approximately correct (PAC) Bayes bound theory provides a theoretical framework to analyze the generalization performance for meta-learning with an explicit numerical generalization error upper bound. A tighter upper bound may achieve better generalization performance. However, for the PAC-Bayes meta-learning bound, the prior distribution is selected randomly which results in poor generalization performance. In this paper, we derive three novel generalization error upper bounds for meta-learning based on the PAC-Bayes relative entropy bound. Furthermore, in order to avoid randomly prior distribution, based on the empirical risk minimization (ERM) method, a data-dependent prior for the PAC-Bayes meta-learning bound algorithm is developed and the sample complexity and computational complexity are analyzed. The experiments illustrate that the proposed three PAC-Bayes bounds for meta-learning achieve a competitive generalization guarantee, and the extended PAC-Bayes bound with a data-dependent prior can achieve rapid convergence ability.

This paper empirically analyses the impact of changes to the set of training examples on the neural network error surface. Specific quantitative characteristics of the error surface related to properties such as ruggedness, modality and structure are measured and visualized as the set of training examples changes. Both the case of random subsampling and active learning from a fixed dataset are examined, producing ten different training scenarios. For each scenario eleven error surface characteristics are calculated for five common benchmark problems. The results demonstrate that the error surface characteristics calculated using only a subsample of the available data commonly do not generalize to that of the full dataset. The observed error surface characteristics are significantly impacted by the particular set of examples used to calculate error. Some error surface characteristics are significantly altered by small changes in the set of examples used to calculate error. The main finding from this study is that when the set of training examples may change during training the training of a neural network is in essence a dynamic optimization problem, suggesting that optimization algorithms developed specifically to solve dynamic optimization problems may be more efficient at training neural networks under such conditions.

Methods based on Graph Convolutional Networks (GCN) for skeleton-based action recognition have achieved great success due to their ability to exploit graph structural information from skeleton data. Recently, the bone information has attracted considerable attention as an effective modality which complements the more conventional joint information for action recognition. However, most existing GCN-based methods extract the joint and bone features with two separate GCN networks, ignoring the dependencies between them. In this paper, a novel GCN model is proposed to exploit the information across joints, bones and their relationship collaboratively on a single undirected graph instead of two separate networks. We call the proposed model Vertex-Edge Graph Convolutional Network (VE-GCN) since it conducts the graph convolution operation on the sampling area containing the designated vertexes from joints and edges from bones, respectively. In addition to conducting the Vertex-Edge graph convolution based on the physical connections of the skeleton, we further apply the Vertex-Edge graph convolution to the non-physical joint-joint and joint-bone connections to capture the distal dependencies, and then the convolution results on the non-physical connections are incorporated into the VE-GCN. Moreover, the Conditional Random Field (CRF) is adopted as the loss function to achieve the task of action recognition. Experimental results on four challenging benchmarks (NTU RGB+D, NTU RGB+D 120, N-UCLA, SYSU) show that the proposed model achieves state-of-the-art performance.

Recursive least mean p-power extreme learning machine (RLMP-ELM) is a newly proposed online machine learning algorithm and is able to provide a robust online prediction of the datasets with noises of different statistics. To further explore the proposed RLMP-ELM to be used in real-world embedded systems, a generic serial FPGA-based hardware architecture of RLMP-ELM is presented in this paper. The entire hardware architecture of RLMP-ELM includes three serial processing modules, which are implemented parameterizably and can be adapted for different application requirements. The hardware framework is in a serial fashion, but parallelization efforts are focused on the processes with high computing complexity by analysis of potential inter-task dependency. To overcome the limitation of memory bandwidth, the block RAM and ping-pong on-chip buffer are applied to improve the computational throughput. The validation experiments are performed through five datasets with different p values. Accuracy results show that our implementation on FPGA could achieve similar accuracy compared to 64-bit floating-point software implementation. We also report and compare hardware performance of our proposed architecture with other existing implementations. The results show that our hardware architecture offers the excellent balance among accuracy, logic occupation and hardware performance.

Fraud detection is essential for e-commerce platforms to maintain a fair business environment. Many existing works propose manually designed methods such as label propagation and dense block mining rules on built user-item graphs to detect fraud behaviours, but they are always heuristic and thus have limited performance. Other learning-based methods can either handle only the fraud detection problem well in the transductive scenario when there is only structural information or require rich content features to obtain a good inductive ability. Considering that content features are not always available in practice and there are usually many fraudulent behaviours that belong to newly emerging users and items, how to learn effective inductive rules with structures only is still underexplored. In this paper, we propose a subgraph-based method named SubGNN for collective fraud detection. In SubGNN, first, we extract the subgraphs around the given edges (user behaviours) to be tested. Then, we remove nodes’ global IDs so that SubGNN is entity-independent. Finally, by learning knowledge reasoning rules on extracted heterogeneous subgraphs using our proposed relational graph isomorphism network (R-GIN), a powerful graph neural network (GNN) model, SubGNN can achieve precise fraud detection. Experiments are conducted on publicly available Amazon and Yelp datasets and a newly collected Taobao dataset. The results clearly show the advantages and prospects of our method. When using SubGNN to detect fraudulent transactions on Taobao, the precision is higher than 0.99 and more than 90 % of fraud samples are recalled.

Rain removal from a single image is a challenging and significant task of image pre-processing. In this paper, we learn the multi-scale streaks from rainy images using feature pyramid, and to improve the effectiveness of the learning, we focus on the feature propagation re-usage and propagation in the extremely deep de-raining network. Specifically, we design a de-raining2 unit and propose a novel deep de-raining network, respectively, called Pyramid Fully Residual Unit and Network (PFR-Unit and PFR-Net). The PFR-Unit employs fully residual learning in each level of feature pyramid and the PFR-Net connects PFR-Units by a compact dense architecture. The fully residual learning encourages the feature re-usage in PFR-Unit by performing identity mapping for all available shortcuts. The compact dense connection strengthens the feature propagation between the PFR-Units and ensures the unicity of the learning space for the PFR-Units. Along with negative SSIM loss, the PFR-Net presents a good performance in single image de-raining. Comprehensive experimental results show that the PFR-Net outperforms the state-of-the-art single de-raining methods with a big margin on Rain100H, Rain100L and Rain1200 datasets.

This paper focuses on the recognition problem of dynamical patterns consisting of sampling sequences. Specifically, based on the concept of structural stability, a novel similarity measure for dynamical patterns is first given. Then, a specific realization is provided, which consists of: (1) an approximation scheme for computation of partial derivative information by utilizing the knowledge learned through deterministic learning; (2) a similarity comparison scheme using the recognition errors generated from the discrete-time dynamical estimators; and (3) performance analysis of the recognition scheme with general recognition conditions. Compared with the existing methods, in which misrecognition may occur when the differences of dynamics between adjacent training patterns are very small, the proposed method is more appealing in the sense that, the partial derivatives of dynamics are introduced to complement the similarity measures, such that the recognition performance is much improved. Simulation studies are conducted to verify the proposed method in a relatively large data set.

Video dehazing is of crucial importance to the outdoor surveillance, and its main challenges mainly come from the spatial-temporal coherence and computational efficiency. This paper presents an efficient real-time video dehazing approach via incremental transmission learning and spatial-temporally coherent regularization, while explicitly suppressing the possible visual artifacts. First, we propose to initialize the transmission map frame-by-frame by a boundary constrained open dark channel model. Then, supposing a scene point yields highly correlated transmission values between adjacent frames, we impose a temporally coherent term to maintain the temporal consistency of consecutive transmission values, and simultaneously derive an incremental transmission adjusting term to adapt the abrupt scene depth changes between the adjacent frames. Accordingly, the highly correlated and spatial-temporally coherent transmission maps can be optimized for each video frame dehazing, whereby the flickering artifacts can be well reduced. Finally, we group each haze/haze-free images in pair and further utilize the guided joint bilateral filter to suppress the visual artifacts that possibly amplified during the dehazing process. The experimental results show that the proposed video dehazing approach is able to well preserve the spatial-temporal coherence, runs sufficiently fast, and also performs favorably compared to the state-of-the-art methods.

Metallic pieces are typically machined by continuous tool passes, which usually causes regular patterns in the form of straight edges in the surface of the pieces. An irregular pattern on the surface of the piece implies a decrease of the quality of the machined piece. In this paper, we propose an acquisition system and a machine-vision based method to describe the texture of the inner and outer surfaces of machined pieces with cylindrical holes. In order to capture images of the hole surface, we used a microscope camera connected to a rigid industrial boroscope. Considering the extracted texture descriptors, a significant correlation is shown. Consequently, the feature vector is reduced and then classified by several algorithms using an exhaustive grid search strategy with 10-fold cross validation. Best results are achieved with the Extremely Randomized Trees classifier with a mean test score on the hold out set of 92.98%, what improves previous research and meets the requirements of the field.

Face recognition systems are widely used for target recognition and identity authentication, such as automated teller machines, mobile phones, and entrance guard systems. However, face recognition systems are vulnerable to presentation attacks, such as photo, replay, and 3D mask attacks. In particular, silicone mask attacks pose a greater threat to face recognition systems because high-quality silicone masks do living properties. To promote the development of face anti-spoofing detection algorithms for silicone mask attacks, this paper constructs a Silicone Mask Face Motion Video Dataset (SMFMVD) containing 200 real face videos and 200 silicone mask face videos. These videos include different facial motions collected from 20 subjects. Moreover, inspired by the observation that the silicone mask face’s facial movement is not so natural as the real face, we propose a novel silicone mask face anti-spoofing detection method based on visual saliency and facial motion characteristics. Specifically, we compute the visual saliency map of a given face image by simulating two kinds of eye movement behaviors, namely “gaze” and “saccade”. Then, we propose a saliency-weighted histogram of local binary pattern operator to extract facial texture features in spatial domain and a saliency-guided histogram of oriented optical flow operator to extract facial motion features in temporal domain. Finally, the support vector machine is used to fuse two groups of facial features to distinguish real and spoof faces. Extensive experiments on public and self-built datasets show its superiority over the state-of-the-art methods.

The traditional robust principal component analysis (RPCA) via decomposition into low-rank plus sparse matrices offers a powerful framework for a large variety of applications in computer vision. However, the reconstructed image experiences serious interference by Gaussian noise, resulting in the degradation of image quality during the denoising process. Thus, a novel manifold constrained joint sparse learning (MCJSL) via non-convex regularization approach is proposed in this paper. Morelly, the manifold constraint is adopted to preserve the local geometric structures and the non-convex joint sparsity is introduced to capture the global row-wise sparse structures. To solve MCJSL, an efficient optimization algorithm using the manifold alternating direction method of multipliers (MADMM) is designed with closed-form solutions and it achieves a fast and convergent procedure. Moreover, the convergence is analyzed mathematically and numerically. Comparisons among the proposed MCJSL and some state-of-the-art solvers, on several accessible datasets, are presented to demonstrate its superiority in image denoising and background subtraction. The results indicate the importance to incorporate the manifold learning and non-convex joint sparse regularization into a general RPCA framework.

In this paper, we develop a novel Joint Model Compression (referred to as JMC) method by combining structured pruning and dense knowledge distillation techniques to significantly compress original large language model into a deep compressed shallow network. In particular, a new Direct Importance-aware Structured Pruning (referred as DISP) approach is proposed to structurally prune the redundant structures in the Transformer networks directly based on the corresponding parameter matrices in the model. Besides, a Dense Knowledge Distillation (referred to as DKD) method is developed with a many-to-one layer mapping strategy to leverage more comprehensive layer-wise linguistic knowledge for the distillation. Further, the proposed structured pruning and dense knowledge distillation are integrated together to perform the joint compression, which enables us to achieve a significant compression without sacrificing model accuracy. The extensive experimental results across four NLP tasks on seven datasets demonstrate its effectiveness and superiority to the baselines, while maintaining similar performance to original large model with further remarkable benefits for inference-time speedup and memory efficiency.

The fitness landscape is a theory applied to the evolutionary dynamics of biological evolution to explain the behavior of evolutionary algorithms in the solution of optimization problems. With the continuous advancement of evolutionary algorithm optimization, a fitness landscape can present more abundant feature information, such as the local fitness, fitness distance correlation, and landscape roughness. These landscape features reflect the optimal solution distribution, quantity, and local unimodal topology of the optimization problem from various angles. This paper expresses the adaptability landscape features of typical optimization problems, engages in a quantitative analysis of the fitness distance correlation information, evaluates the difficulty of solving the problem within the search space, and obtains the correlation degree classification result. The search strategy adapts the mixed mutation and the fitness distance correlation for differential evolution. Empirical studies show that, the fitness distance correlation search strategy for the differential evolution algorithm can avoid falling into the local optimum, improve accuracy and convergence, and solve the single-objective optimization problem in a more comprehensive manner.