Instance-level human parsing is aimed at separately partitioning the human body into different semantic parts for each individual, which remains a challenging task due to human appearance/pose variation, occlusion and complex backgrounds. Most state-of-the-art methods follow the “parsing-by-detection” paradigm, which relies on a trained detector to localize persons and then sequentially performs single-person parsing for each person. However, this paradigm is closely related to the detector, and the runtime is proportional to the number of persons in an image. In this paper, we present a novel detection-free framework for instance-level human parsing in an end-to-end manner. We decompose instance-level human parsing into two subtasks via a unified network: 1) semantic segmentation for pixel-level classification as a human part and 2) instance segmentation for mask-level classification as a person. The framework can directly predict the human-part semantic mask for all persons and binary masks for instance-level persons in parallel. The parsing result of each person can be acquired via a Hadamard product between the human-part semantic mask and the corresponding person's binary mask. Extensive experiments demonstrate that our proposed method performs favorably against state-of-the-art methods on the CIHP and MHP v2 datasets.

When performing evolutionary optimization for computationally expensive objective, surrogate-assisted evolutionary algorithm(SAEA) is an effective approach. However, due to the limited availability of data in these scenarios, it can be challenging to create a highly accurate surrogate model, leading to reduced optimization effectiveness. To address this issue, we propose an Interpretable Convolution Network(ICN) for offline surrogate-assited evolutionary optimization. ICN retains the non-linear expression ability of traditional neural networks, while possessing the advantages of clear physical structure and the ability to incorporate prior knowledge during network parameter design and training process. We compare ICN-SAEA with tri-training method(TT-DDEA) and model-ensemble method(DDEA-SA) in several benchmark problems. Experimental results show that ICN-SAEA is better in searching optimal solution than compared algorithms.

This paper studied music feature recognition and classification. First, the common signal features were analyzed, and the signal pre-processing method was introduced. Then, the Mel–Phon coefficient (MPC) was proposed as a feature for subsequent recognition and classification. The deep belief network (DBN) model was applied and improved by the gray wolf optimization (GWO) algorithm to get the GWO–DBN model. The experiments were conducted on GTZAN and free music archive (FMA) datasets. It was found that the best hidden-layer structure of DBN was 1440-960-480-300. Compared with machine learning methods such as decision trees, the DBN model had better classification performance in recognizing and classifying music types. The classification accuracy of the GWO–DBN model reached 75.67%. The experimental results demonstrate the reliability of the GWO–DBN model. The GWO–DBN model can be further promoted and applied in actual music research.

Surrogate-based-constrained optimization for some optimization problems involving computationally expensive objective functions and constraints is still a great challenge in the optimization field. Its difficulties are of two primary types. One is how to handle the constraints, especially, equality constraints; another is how to sample a good point to improve the prediction of the surrogates in the feasible region. Overcoming these difficulties requires a reliable constraint-handling method and an efficient infill-sampling strategy. To perform inequality- and equality-constrained optimization of expensive black-box systems, this work proposes a hybrid surrogate-based-constrained optimization method (HSBCO), and the main innovation is that a new constraint-handling method is proposed to map the feasible region into the origin of the Euclidean subspace. Thus, if the constraint violation of an infeasible solution is large, then it is far from the origin in the Euclidean subspace. Therefore, all constraints of the problem can be transformed into an equivalent equality constraint, and the distance between an infeasible point and the origin in the Euclidean subspace represents the constraint violation of the infeasible solution. Based on the distance, the objective function of the problem can be penalized by a Gaussian penalty function, and the original constrained optimization problem becomes an unconstrained optimization problem. Thus, the feasible solutions of the original minimization problem always have a lower objective function value than any infeasible solution in the penalized objective space. To improve the optimization performance, kriging-based efficient global optimization (EGO) is used to find a locally optimal solution in the first phase of HSBCO, and starting from this locally optimal solution, RBF-model-based global search and local search strategies are introduced to seek global optimal solutions. Such a hybrid optimization strategy can help the optimization process converge to the global optimal solution within a given maximum number of function evaluations, as demonstrated in the experimental results on 23 test problems. The method is shown to achieve the global optimum more closely and efficiently than other leading methods.

Evolutionary multiobjective clustering (MOC) algorithms have shown promising potential to outperform conventional single-objective clustering algorithms, especially when the number of clusters k is not set before clustering. However, the computational burden becomes a tricky problem due to the extensive search space and fitness computational time of the evolving population, especially when the data size is large. This article proposes a new, hierarchical, topology-based cluster representation for scalable MOC, which can simplify the search procedure and decrease computational overhead. A coarse-to-fine-trained topological structure that fits the spatial distribution of the data is utilized to identify a set of seed points/nodes, then a tree-based graph is built to represent clusters. During optimization, a bipartite graph partitioning strategy incorporated with the graph nodes helps in performing a cluster ensemble operation to generate offspring solutions more effectively. For the determination of the final result, which is underexplored in the existing methods, the usage of a cluster ensemble strategy is also presented, whether k is provided or not. Comparison experiments are conducted on a series of different data distributions, revealing the superiority of the proposed algorithm in terms of both clustering performance and computing efficiency.

In the past several years, it has become apparent that the effectiveness of Pareto-dominance-based multiobjective evolutionary algorithms deteriorates progressively as the number of objectives in the problem, given by M , grows. This is mainly due to the poor discriminability of Pareto optimality in many-objective spaces (typically M ≥ 4 ). As a consequence, research efforts have been driven in the general direction of developing solution ranking methods that do not rely on Pareto dominance (e.g., decomposition-based techniques), which can provide sufficient selection pressure. However, it is still a nontrivial issue for many existing non-Pareto-dominance-based evolutionary algorithms to deal with unknown irregular Pareto front shapes. In this article, a new many-objective evolutionary algorithm based on the generalization of Pareto optimality (GPO) is proposed, which is simple, yet effective, in addressing many-objective optimization problems. The proposed algorithm used an "( M-1 ) + 1" framework of GPO dominance, ( M-1 )-GPD for short, to rank solutions in the environmental selection step, in order to promote convergence and diversity simultaneously. To be specific, we apply M symmetrical cases of ( M-1 )-GPD, where each enhances the selection pressure of M-1 objectives by expanding the dominance area of solutions, while remaining unchanged for the one objective left out of that process. Experiments demonstrate that the proposed algorithm is very competitive with the state-of-the-art methods to which it is compared, on a variety of scalable benchmark problems. Moreover, experiments on three real-world problems have verified that the proposed algorithm can outperform the others on each of these problems.

Dynamic multiobjective optimization problems (DMOPs) challenge multiobjective evolutionary algorithms (MOEAs) because those problems change rapidly over time. The class of DMOPs whose objective functions change over time steps, in ways that exhibit some hidden patterns has gained much attention. Their predictability indicates that the problem exhibits some correlations between solutions obtained in sequential time periods. Most of the current approaches use linear models or similar strategies to describe the correlations between historical solutions obtained, and predict the new solutions in the following time period as an initial population from which the MOEA can begin searching in order to improve its efficiency. However, nonlinear correlations between historical solutions and current solutions are more common in practice, and a linear model may not be suitable for the nonlinear case. In this paper, we present a support vector regression (SVR)-based predictor to generate the initial population for the MOEA in the new environment. The basic idea of this predictor is to map the historical solutions into a high-dimensional feature space via a nonlinear mapping, and to do linear regression in this space. SVR is used to implement this process. We incorporate this predictor into the MOEA based on decomposition (MOEA/D) to construct a novel algorithm for solving the aforementioned class of DMOPs. Comprehensive experiments have shown the effectiveness and competitiveness of our proposed predictor, comparing with the state-of-the-art methods.

This paper introduces a differential prediction model to predict the varying Pareto-Optimal Solutions (POS) when solving dynamic multiobjective optimization problems (DMOPs). In dynamic multiobjective optimization problems, several competing objective functions and/or constraints change over time. As a consequence, the Pareto-Optimal Solutions and/or Pareto-Optimal Front may vary over time. The differential prediction model is used to forecast the shift vector in the decision space of the centroid in the population through the centroid's historical locations in three previous environments. This differential prediction model is incorporated into a multiobjective evolutionary algorithm based on decomposition to solve DMOPs. After detecting the environmental change, half of individuals in the population are forecasted their new positions in the decision space by using the differential prediction model and the others' positions are retained. The proposed model is tested on a number of typical benchmark problems with several dynamic characteristics. Experimental results show that the proposed model is competitively in comparisons with the other state-of-the-art models or approaches that were proposed for solving DMOPs.

In this paper, a text similarity computation method named VSM-Cilin which is based on semantic vector space model is proposed in the background of radio station. VSM-Cilin improved the traditional VSM in the following areas. First, consider the semantic relations between words. Second, use semantic resources to reduce dimension. Third, use inverted index to filter out candidate document set. Forth, take the weight of the feature item into consideration when compute the similarity. The experiments show that the accuracy of VSM-Cilin is significantly improved compared with the traditional vector space model and the method of bidirectional mapping based on HITIR-Lab Tongyici Cilin.

This paper presents an indirect adaptive fuzzy control scheme for a class of MIMO non-affine nonlinear systems with unknown dynamics and actuator saturation for greenhouse climate control problems. The objective is to implement output tracking control on nonlinear systems. Using feedback linearization, control inputs with known control gains are first synthesized by well-modeled dynamics of the system, and Taylor series expansion is used to transform unknown non-affine dynamics into the corresponding affine forms. Fuzzy logic systems (FLS) are introduced to estimate the unknown nonlinearity of the transformed affine system and the saturation nonlinearity due to the actuator constraint. The control inputs corresponding to nonlinearity are constructed based on the estimations. By introducing a robust control term, estimation errors and external disturbances are well handled, so as to guarantee the stability when tracking the control process. The control gain estimation obtained by FLS is modified to avoid singularity. Lyapunov stability analysis is performed to derive the adaptive law. To validate the effectiveness of the proposed control scheme, we apply it to a greenhouse climate control problem. The ventilation rate in the greenhouse model is unknown; therefore, it is estimated by FLS. The simulation exhibits satisfactory results, in which the temperature and humidity inside the greenhouse are well tracked.

The vast majority of multiobjective evolutionary algorithms presented to date are Pareto-based. Usually, these algorithms perform well for problems with few (two or three) objectives. However, due to the poor discriminability of Pareto-optimality in many-objective spaces (typically four or more objectives), their effectiveness deteriorates progressively as the problem dimension increases. This paper generalizes Pareto-optimality both symmetrically and asymmetrically by expanding the dominance area of solutions to enhance the scalability of existing Pareto-based algorithms. The generalized Pareto-optimality (GPO) criteria are comparatively studied in terms of the distribution of ranks, the ranking landscape, and the convergence of the evolutionary process over several benchmark problems. The results indicate that algorithms equipped with a generalized optimality criterion can acquire the flexibility of changing their selection pressure within certain ranges, and achieve a richer variety of ranks to attain faster and better convergence on some subsets of the Pareto optima. To compensate for the possible diversity loss induced by the generalization, a distributed evolution framework with adaptive parameter setting is also proposed and briefly discussed. Empirical results indicate that this strategy is quite promising in diversity preservation for algorithms associated with the GPO.

This paper presents a foreground detection algorithm that is robust against illumination changes and noise, and provides a novel and practical choice for intelligent video surveillance systems using static cameras. This paper first introduces an online expectation-maximization algorithm that is developed from a basic batch version to update Gaussian mixture models in real time. Then, a spherical K-means clustering method is combined to provide a more accurate direction for the update when illumination is unstable. The combination is supported by the linearity of RGB color reflected from object surfaces, which is both theoretically proved by spectral reflection theory and experimentally validated in several observations. Foreground detection is carried out using a statistical framework with regional judgment. Noise in the detection stage is further reduced by a Bayesian iterative decision-making step. The experiments show that the proposed algorithm outcompetes several classical methods on several datasets, both in detection performance and in robustness to perturbations from illumination changes.

This work proposes a fast background learning algorithm for foreground detection under changing illumination. Gaussian Mixture Model (GMM) is an effective statistical model in background learning. We first focus on Titterington's online EM algorithm that can be used for real-time unsupervised GMM learning, and then advocate a deterministic data assignment strategy to avoid Bayesian computation. The color of the foreground is apt to be influenced by the environmental illumination that usually produce undesirable effect for GMM updating, however, a collinear feature of pixel intensity under changing light is discovered in RGB color space. This feature is afterward used as a reliable clue to decide which part of mixture to update under changing light. A foreground detection step proposed in early version of this work is employed to extract foreground objects by comparing the estimated background model with the current video frame. Experiments have shown the proposed method is able to achieve satisfactory static background images of scenes as well as is also superior to some mainstream methods in detection performance under both indoor and outdoor scenes.

This paper achieves fast and effective pedestrian detection using Histogram of Oriented Gradient (HOG) descriptor based Support Vector Machine (SVM). A novel approach taking advantage of CodeBook background subtraction(CBBS) is presented in this paper to produce pedestrian samples for SVM. HOG features of the samples are extracted to train Linear and RBF SVM classifiers offline. The classifier is adopted as pedestrian detector in online real-time video sequence detection. The influence of various ratios of positive and negative training sets on detector's performance is carefully investigated. We also compare Linear and RBF SVM in experiments as well. It is concluded that robust feature extraction, proper positive and negative training sample construction, and fine kernel function are crucial for good classification results. Experiments prove that our detector obtains a reliable detection result, which not only satisfies real-time requirement, and is robust against pedestrian appearance and pose variations, illumination changes, background changes, shadows and etc.

This paper investigates the issue of PID-controller parameters tuning for a greenhouse climate control system using Evolutionary Algorithms based on multiple performance measures such as good set-point tracking and smooth control signals. A model of nonlinear thermodynamic laws between numerous system variables affecting the greenhouse climate is formulated. The proposed tuning scheme is validated for greenhouse climate control by minimizing the integrated time square error (ITSE) and the control increment or rate in a series of simulations. The results show that the controllers by tuning the gain parameters can achieve good control performance through step responses such as small overshoot, fast settling time, and less rise time and steady state error. Maybe it is quite an effective and promising tuning method using multi-objective algorithms in the complex greenhouse production.

This paper presents a background modeling algorithm and a foreground detecting method which is robust against illumination change, providing a novel and practical choice for intelligent video surveillance systems using static cameras. This paper first introduces an online Expectation Maximization algorithm which is developed from the basic batch edition to update the mixture models in real time. Then a spherical K-means clustering method is used to provide more accurate direction for the update of Gaussian Mixture Models after a deep study of RGB space features under illumination changes. Foreground detection is carried out using a statistical framework and RGB pixel intensity judgments. The results show the proposed algorithm outcompete several classic methods in efficiency, accuracy, and robustness to perturbations from illumination changes, on a sampling of problems.

This paper presents a hybrid control strategy, combining RBF network with the conventional PID controller, for the greenhouse climate control. A model of nonlinear thermodynamic laws between numerous system variables affecting the greenhouse climate is formulated. The presented Neuro-PID control scheme is validated through simulations of set-point tracking and disturbance rejection. The results show that the proposed strategy has good adaptability, strong robustness while achieving satisfactory control performance for the complex and nonlinear time-varying greenhouse climate control system, and it may provide a valuable reference to formulate environmental control strategies for actual application in greenhouse production.

Trajectory tracking of the mobile robot is one research hot for the robot. For the control system of the two-wheeled differential drive mobile robot being in nonhonolomic system and the complex relations among the control parameters, it is difficult to solve the problem based on traditional mathematics model. A new control scheme combined with the fuzzy PD (Proportional and Differential) control and the separate integral control is proposed in this paper. The control scheme can not only make full use of the advantage of the fuzzy control, but also have the good steady state tracking ability of the integral control. However, this control scheme introduces so many parameters which are difficult to optimize. In order to realize the online adaptive learning of the control parameters, the modified VFSA (Very Fast Simulated Annealing) is used. The simulation results show that the method is feasible, and can quickly approach the conference trajectory in a short time, and the trajectory tracking error is very small.

It is popular that there exist multiple objectives in practical control system. To solve this problem, a dynamic multi-objective control algorithm based on NSGA-II is presented. Based on the multi-objective evolutionary algorithm and the tight relation between the system states of the neighboring sampling instants, a multi-objective iterative compatible control algorithm is proposed which can cope with both the convex/non-convex control problem as well as improve the computing speed. Considering the two objectives speed and energy cost in the control of IPMCs propelled robotic fish, the algorithm is successfully applied to it to illuminate its validity. The result also shows the potential for the multi-objective evolutionary algorithm to the real-time control field.

In this paper we present a novel framework for computing the steady turning motion of a robotic fish undergoing periodic body and/or tail deformation. Taking the turning radius and the angular velocity as unknowns, we obtain the absolute motion trajectories of points on the ldquospinal columnrdquo of robotic fish by superimposing relative body/tail motions on the rigid body circular motion. The hydrodynamic reactive force and the resulting moment are then computed from the motion trajectories, using Lighthill's large-amplitude elongated-body theory, in terms of the two turning parameters. By integrating the dynamics of rigid body motion and averaging out oscillations, implicit equations involving the turning parameters can be established and solved. We also discuss the plan of applying the proposed framework to the modeling of steady turning maneuvers of biomimetic robotic propelled by an ionic polymer-metal composite (IPMC) caudal fin.

This paper presents an adaptive controller design method for a class of system with modeling uncertainties or environment disturbance. The controller has a paralleled structure of Dynamic Matrix Control and PID Control. The weight for each of the controller can be adaptively tuned through iteratively learning. It can make full use of the model information, meanwhile resisting disturbance and overcoming the un-modeled uncertainties in a certain degree. The simulation and comparison with other control method show that this method has better tracking performance, disturbance resistance, robustness and great feasibility to be implemented in engineering application.

This paper propose an IPGA based multi-objective compatible control algorithm to control oversaturated adjacent intersections. The concept of feeding delay and non-feeding delay is introduced; A BPNN method is used to set up a MIMO delay model based on the simulated data got from cell transmission model. Then, the control problem is formulated as an conflicted multi-objective control problem, and the IPGA based multi-objective compatible control algorithm is proposed to solve the control problem. Results show that the proposed algorithm is robust and capable of deal with real-time oversaturated adjacent intersections control problem. The algorithm is tested in a network consisting of a core area of 11 oversaturated intersections. It can be concluded that the proposed method is much more effective in relieving oversaturation in a network than the isolated intersection control strategy.

A new two-layer multi-objective compatible control algorithm is proposed for a class of control problems with two conflicting control objectives, control error and energy consumption. The first layer is devoted to obtaining a user’s desired controlled objectives region, assured to be not only achievable but also Pareto-optimal. The second layer is devoted to designing an effective controller by optimizing the most important controlled objective (such as the energy consumption), subject to system constraints from the controlled objectives region in the first layer. This control algorithm provides an effective robust controller design method for multiobjective control problems with precise models and uncertain initial conditions. Simulations illustrate that the two-layer multi-objective compatible control (MOCC) algorithm has some advantages over traditional multi-objective control methods.

The purpose of this paper is to investigate the application of particle swarm optimization (PSO) algorithm in solving the traffic signal timing optimization problem. A local fuzzy-logic controller (FLC) installed at each junction is used to provide some initial solutions for the particle swarm optimization algorithm. Coordination parameters from adjacent junctions are taken into consideration by local fuzzy-logic controller. The membership functions and the rules of the fuzzy logic controller (FLC) are optimized using the standard particle swarm optimization (SPSO) algorithm. A new particle swarm optimization algorithm is used to optimize the average delay and average number of stops for adjacent junctions and to handle the constraints. The simulation results show that the delay per vehicle can be substantially reduced under constant traffic demands and time-varying traffic demands, particularly when the traffic demands on the upstream is larger than the traffic demand on the downstream. The implementation of this method does not require complicated hardware, and such simplicity makes it a useful tool for offline studies or real-time control purposes

A new design of GFNN (generalized fuzzy neural network) based on T-S (Takagi-Sugeno) model and its corresponding off-line and on-line architecture and parameter identification algorithm are presented. The TS-GFNN, which integrates the advantages of neural network into that of the fuzzy logic system, is a powerful method in the modeling of the nonlinear system. Clustering based membership function is introduced in the premise of TS-GFNN, which make the architecture more concise. The on-line identification algorithm can make the TS-GFNN to be more adaptive in the design of controller. The simulation shows that the identifier based on TS-GFNN can approach the non-linear function in any precision, and it is more effective than the ordinary method