Volume 14, Number 4, 2017
Functional connectivity has emerged as a promising approach to study the functional organisation of the brain and to define features for prediction of brain state. The most widely used method for inferring functional connectivity is Pearson s correlation, but it cannot differentiate direct and indirect effects. This disadvantage is often avoided by computing the partial correlation between two regions controlling all other regions, but this method suffers from Berkson s paradox. Some advanced methods, such as regularised inverse covariance, have been applied. However, these methods usually depend on some parameters. Here we propose use of minimum partial correlation as a parameter-free measure for the skeleton of functional connectivity in functional magnetic resonance imaging (fMRI). The minimum partial correlation between two regions is the minimum of absolute values of partial correlations by controlling all possible subsets of other regions. Theoretically, there is a direct effect between two regions if and only if their minimum partial correlation is non-zero under faithfulness and Gaussian assumptions. The elastic PC-algorithm is designed to efficiently approximate minimum partial correlation within a computational time budget. The simulation study shows that the proposed method outperforms others in most cases and its application is illustrated using a resting-state fMRI dataset from the human connectome project.
Evaluating individuals personality traits and intelligence from their faces plays a crucial role in interpersonal relationship and important social events such as elections and court sentences. To assess the possible correlations between personality traits (also measured intelligence) and face images, we first construct a dataset consisting of face photographs, personality measurements, and intelligence measurements. Then, we build an end-to-end convolutional neural network for prediction of personality traits and intelligence to investigate whether self-reported personality traits and intelligence can be predicted reliably from a face image. To our knowledge, it is the first work where deep learning is applied to this problem. Experimental results show the following three points:1) "Rule-consciousness" and "Tension" can be reliably predicted from face images. 2) It is difficult, if not impossible, to predict intelligence from face images, a finding in accord with previous studies. 3) Convolutional neural network (CNN) features outperform traditional handcrafted features in predicting traits.
Existing tracking algorithms often suffer from the drift and lost problems caused by factors such as pose variation, illumination change, occlusion and motion. Therefore, developing a robust and effective tracker is still a challenging task. In this paper, we propose a real-time compressive tracking based on online Hough forest. The gray and texture features of discrete samples are extracted and compressed via the random measurement matrix. Online Hough forest classifier is used to vote the location probability of the target, and it optimizes the confidence map estimation for the target detection. The location of target being tracked is determined by combining the upper frame of the target center location and the probability confidence map of the incremental Hough forest. Finally, the classifier parameters are updated online by introducing the illumination variation and target occlusion feedback mechanism adaptively. The experiments with state-of-the-art algorithms on challenging sequences demonstrated that the proposed algorithm can effectively enhance the robustness and accuracy, and inherit the real-time performance of the compressive tracking algorithm.
In order to solve the problem of indoor place recognition for indoor service robot, a novel algorithm, clustering of features and images (CFI), is proposed in this work. Different from traditional indoor place recognition methods which are based on kernels or bag of features, with large margin classifier, CFI proposed in this work is based on feature matching, image similarity and clustering of features and images. It establishes independent local feature clusters by feature cloud registration to represent each room, and defines image distance to describe the similarity between images or feature clusters, which determines the label of query images. Besides, it improves recognition speed by image scaling, with state inertia and hidden Markov model constraining the transition of the state to kill unreasonable wrong recognitions and achieves remarkable precision and speed. A series of experiments are conducted to test the algorithm based on standard databases, and it achieves recognition rate up to 97% and speed is over 30fps, which is much superior to traditional methods. Its impressive precision and speed demonstrate the great discriminative power in the face of complicated environment.
Surface particles growing in large aperture optical element (LAOE) have significant impact on LAOE s stable operation. It is a challenge for the online system to inspect the particles with long working distance, enough precision and high efficiency because of the system constraints. In this paper, an effective and portable inspection instrument is designed based on dark-field imaging principle. A Nikon lens and an industrial high definition (HD) camera are selected to construct the vision system to inspect particles of microns size spreading over hundreds of millimeters. Using two motors and other mechanical structure, the system can realize auto-focus and image rectification functions. The line light sources are installed on both sides of the LAOE in a sealed box while the vision system is portable and working outside the box. An adaptive binarization method is proposed to process the captured dark-field image. The distribution of particles on the LAOE s surface is investigated. Because of the high resolution of the captured image, the SSE2 instructions optimization method is used to reduce the time cost of the algorithm. Experiments show that the instrument can inspect LAOE effectively and accurately.
Parallel mechanisms are widely used in various fields of engineering and industrial applications such as machine tools, flight simulators, earthquake simulators, medical equipment, etc. Parallel mechanisms are restricted to some limitations such as irregular workspace, existence of singular points and complexity of control systems which should be studied and analyzed for effective and efficient use. In this research, a new machine tool with parallel mechanism which has three translational degrees of freedom is studied and the workspace and singular points are determined by deriving analytical equations and then utilizing of Matlab software. To do so, forward and inverse kinematics of the mechanism are obtained and workspace and singular points are calculated using a search algorithm. Afterward, in order to validate the results, the proposed mechanism is simulated in automatic dynamics analysis of mechanical systems (ADAMS) software. Moreover, in order to investigate the quality of robot performance and dexterity of the mechanism in its workspace, global dexterity index (GDI) of the robot is calculated using Jacobean matrix at different positions of the mobile platform.
A new semi-blind adaptive beamforming scheme is proposed for multi-input multi-output (MIMO) induced and spacedivision multiple-access based wireless systems that employ high order phase shift keying signaling. A minimum number of training symbols, very close to the number of receiver antenna elements, are used to provide a rough initial least squares estimate of the beamformer s weight vector. A novel cost function combining the constant modulus criterion with decision-directed adaptation is adopted to adapt the beamformer weight vector. This cost function can be approximated as a quadratic form with a closed-form solution, based on which we then derive the recursive least squares (RLS) semi-blind adaptive beamforming algorithm. This semi-blind adaptive beamforming scheme is capable of converging fast to the minimum mean-square-error beamforming solution, as demonstrated in our simulation study. Our proposed semi-blind RLS beamforming algorithm therefore provides an efficient detection scheme for the future generation of MIMO aided mobile communication systems.
This paper presents the design of sliding mode controller for the output regulation of single input single output (SISO) nonlinear systems. The sliding surfaces are designed to force the error dynamics to follow proportional (P), proportional integral (PI) and proportional integral derivative (PID) dynamics. The controller parameters are obtained using probabilistic particle swarm optimization technique. A judicious selection of various sliding surfaces based on the relative degree of the systems is also elaborated. A detailed comparison of the output regulation for various systems with different relative degree is presented. Numerical simulation shows the effectiveness of the proposed method and robustness of the sliding mode controller.
The paper presents readily implementable approaches for fault detection and diagnosis (FDD) based on measurements from multiple sensor groups, for industrial systems. Specifically, the use of hierarchical clustering (HC) and self-organizing map neural networks (SOMNNs) are shown to provide robust and user-friendly tools for application to industrial gas turbine (IGT) systems. HC fingerprints are found for normal operation, and FDD is achieved by monitoring cluster changes occurring in the resulting dendrograms. Similarly, fingerprints of operational behaviour are also obtained using SOMNN based classification maps (CMs) that are initially determined during normal operation, and FDD is performed by detecting changes in their CMs. The proposed methods are shown to be capable of FDD from a large group of sensors that measure a variety of physical quantities. A key feature of the paper is the development of techniques to accommodate transient system operation, which can often lead to false-alarms being triggered when using traditional techniques if the monitoring algorithms are not first desensitized. Case studies showing the efficacy of the techniques for detecting sensor faults, bearing tilt pad wear and early stage pre-chamber burnout, are included. The presented techniques are now being applied operationally and monitoring IGTs in various regions of the world.
In this paper, a robust fractional order fuzzy P + fuzzy I + fuzzy D (FOFP + FOFI + FOFD) controller is presented for a nonlinear and uncertain 2-link planar rigid manipulator. It is a nonlinear fuzzy controller with variable gains that makes it selfadjustable or adaptive in nature. The fractional order operators further make it more robust by providing additional degrees of freedom to the design engineer. The integer order counterpart, fuzzy P + fuzzy I + fuzzy D (FP + FI + FD) controller, for a comparative study, was realized by taking the integer value for the fractional order operators in FOFP + FOFI + FOFD controller. The performances of both the fuzzy controllers are evaluated for reference trajectory tracking and disturbance rejection with and without model uncertainty and measurement noise. Genetic algorithm was used to optimize the parameters of controller under study for minimum integral of absolute error. Simulation results demonstrated that FOFP + FOFI + FOFD controller show much better performance as compared to its counterpart FP + FI + FD controller in servo as well as the regulatory problem and in model uncertainty and noisy environment FOFP + FOFI + FOFD controller demonstrated more robust behavior as compared to the FP + FI + FD controller. For the developed controller bounded-input and bounded-output stability conditions are also developed using Small Gain Theorem.
In this paper, a mathematical model of the photovoltaic (PV) pumping system s main components is firstly established. Then, the design of maximum power point tracking (MPPT) stage that ensures battery charging is described. This work is motivated by the need of photovoltaic generator (PVG) that efficiently extracts maximum power. The PVG is a special source of energy which has nonlinear current-voltage characteristics depending on variations in temperature and solar irradiance. In order to achieve the MPPT operating goals, a special interest is focused on the variable structure sliding mode (SM) control strategy and the classic perturb and observe (P&O) algorithm. The permanent magnet synchronous motor (PMSM) is selected as a pump driver. The field oriented control is performed as the motor drive strategy. Simulation results show a high level of efficiency, obtained with the proposed PV based pumping system. The performance comparison between SM controller and P&O controller has been carried out to demonstrate the effectiveness of the former in drawing more energy and a fast response against irradiation disturbances.