Strong Convergence Analysis of Batch Gradient-Based Learning Algorithm for Training Pi-Sigma Network Based on TSK Fuzzy Models

By combining of the benefits of high-order network and TSK (Tagaki-Sugeno-Kang) inference system, Pi-Sigma network is capable to dispose with the nonlinear problems much more effectively, which means it has a compacter construction, and quicker computational speed. The aim of this paper is to present a gradient-based learning method for Pi-Sigma network to train TSK fuzzy inference system. Moreover, some strong convergence results are established based on the weak convergence outcomes, which indicates that the sequence of weighted fuzzy parameters gets to a fixed point. Simulation results show the modified learning algorithm is effective to support the theoretical results.     

An SNN-Based Semantic Role Labeling Model with Its Network Parameters Optimized Using an Improved PSO Algorithm

Semantic role labeling (SRL) is a fundamental task in natural language processing to find a sentence-level semantic representation. The semantic role labeling procedure can be viewed as a process of competition between many order parameters, in which the strongest order parameter will win by competition and the desired pattern will be recognized. To realize the above-mentioned integrative SRL, we use synergetic neural network (SNN). Since the network parameters of SNN directly influence the synergetic recognition performance, it is important to optimize the parameters. In this paper, we propose an improved particle swarm optimization (PSO) algorithm based on log-linear model and use it to effectively determine the network parameters. Our contributions are two-folds: firstly, a log-linear model is introduced to PSO algorithm which can effectively make use of the advantages of a variety of different knowledge sources, and enhance the decision making ability of the model. Secondly, we propose an improved SNN model based on the improved PSO and show its effectiveness in the SRL task. The experimental results show that the proposed model has a higher performance for semantic role labeling with more powerful global exploration ability and faster convergence speed, and indicate that the proposed model has a promising future for other natural language processing tasks.     

Neural Networks Based PID Control of Bidirectional Inductive Power Transfer System

Inductive power transfer (IPT) systems facilitate contactless power transfer between two sides and across an air-gap, through weak magnetic coupling. However, IPT systems constitute a high order resonant circuit and, as such, are difficult to design and control. Aiming at the control problems for bidirectional IPT system, a neural networks based proportional-integral-derivative (PID) control strategy is proposed in this paper. In the proposed neural PID method, the PID gains, \(K_{P}\), \(K_{I}\) and \(K_{D}\) are treated as Gaussian potential function networks (GPFN) weights and they are adjusted using online learning algorithm. In this manner, the neural PID controller has more flexibility and capability than conventional PID controller with fixed gains. The convergence of the GPFN weights learning is guaranteed using Lyapunov method. Simulations are used to test the effective performance of the proposed controller.     

3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction

With the advent of low-cost 3D sensors and 3D printers, scene and object 3D surface reconstruction has become an important research topic in the last years. In this work, we propose an automatic (unsupervised) method for 3D surface reconstruction from raw unorganized point clouds acquired using low-cost 3D sensors. We have modified the growing neural gas network, which is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation, to perform 3D surface reconstruction of different real-world objects and scenes. Some improvements have been made on the original algorithm considering colour and surface normal information of input data during the learning stage and creating complete triangular meshes instead of basic wire-frame representations. The proposed method is able to successfully create 3D faces online, whereas existing 3D reconstruction methods based on self-organizing maps required post-processing steps to close gaps and holes produced during the 3D reconstruction process. A set of quantitative and qualitative experiments were carried out to validate the proposed method. The method has been implemented and tested on real data, and has been found to be effective at reconstructing noisy point clouds obtained using low-cost 3D sensors.     

Task rescheduling optimization to minimize network resource consumption

An increasing number of big-data services are being deployed in a cloud computing environment, attracted by the on-demand service, rapid elasticity, and low maintenance costs. As a result, ensuring the quality of service has become an important research problem. Traditionally, task rescheduling is used to ensure a consistent quality of service in the event of failure of a virtual machine. However, the network resource consumption of different rescheduling methods varies. To address this problem, we propose a task rescheduling method that minimizes network resource consumption.The method includes three algorithms. The first obtains a set of good virtual machines from the large quantity of service-providing virtual machines using the skyline operation. A ranking algorithm then fuses the data size and the task emergency to identify significant tasks. Finally, we present an algorithm that automatically determines the optimal insertion point for each task. To verify the effectiveness of the proposed method, we extend the renowned simulator CloudSim and conduct a series of experiments. The results show that our method is more efficient than other methods in terms of network resource consumption.     

High-quality image restoration from partial mixed adaptive-random measurements

A novel framework to construct an efficient sensing (measurement) matrix, called mixed adaptive-random (MAR) matrix, is introduced for directly acquiring a compressed image representation. The mixed sampling (sensing) procedure hybridizes adaptive edge measurements extracted from a low-resolution image with uniform random measurements predefined for the high-resolution image to be recovered. The mixed sensing matrix seamlessly captures important information of an image, and meanwhile approximately satisfies the restricted isometry property. To recover the high-resolution image from MAR measurements, the total variation algorithm based on the compressive sensing theory is employed for solving the Lagrangian regularization problem. Both peak signal-to-noise ratio and structural similarity results demonstrate the MAR sensing framework shows much better recovery performance than the completely random sensing one. The work is particularly helpful for high-performance and lost-cost data acquisition.     

DCT statistics-based digital dropout detection in degraded archived media

With the rapid development of visual digital media, the demand for better quality of service has increased the pressure on broadcasters to automate their error detection and restoration activities for preserving their archives. Digital dropout is one of the defects that affect archived visual materials and tends to occur in block by block basis (size of 8 × 8). It is well established that human visual system (HVS) is highly adapted to the statistics of its visual natural environment. Consequently, in this paper, we have formulated digital dropout detection as a classification problem which predicts block label based on statistical features. These statistical features are indicative of perceptual quality relevant to human visual perception, and allow pristine images to be distinguished from distorted ones. Here, the idea is to extract discriminant block statistical features based on discrete cosine transform (DCT) coefficients and determine an optimal neighborhood sampling strategy to enhance the discrimination ability of block representation. Since this spatial frame based approach is free from any motion computation dependency, it works perfectly in the presence of fast moving objects. Experiments are performed on video archives to evaluate the efficacy of the proposed technique.     

Structure compliant local warping of images with applications to watermarking attack

Localized geometric warping of images is known to be one of the most effective attacks against image watermarking systems. However, the existing local geometrical attacks, when applied to images with regular structures, cause perceptible distortion because they are not adaptive to the content of the images. In this work, we present a multi-scale directional smoothing framework in which local displacement vectors are smoothed by locally adaptive directional kernels. Both the displacement vectors for large structures and those for fine structures are constrained by using a multi-scale pyramid. Subjective tests and objective metrics show that our proposed approach can effectively enhance the perceptual quality of the image after geometric attacks. The test of the attacking effects on two typical watermarking systems demonstrates that our approach does not degrade the attacking effects for Markov random field generated displacement field.