Detection Algorithm and Application Based on Work Status Evaluator

Distributed memory and localized memory in neural networks

The construction of a model of the background of a scene still remains as a challenging task in video surveillance systems, in particular for moving cameras. This work presents a novel approach for constructing a panoramic background model based on competitive learning neural networks and a subsequent piecewise linear interpolation by Delaunay triangulation. The approach can handle arbitrary camera directions and zooms for a Pan-Tilt-Zoom (PTZ) camera-based surveillance system. After testing the proposed approach on several indoor sequences, the results demonstrate that the proposed method is effective and suitable to use for real-time video surveillance applications.

Caption graphically superimposed in video frames can provide important indexing information. The automatic detection and recognition of video captions can be of great help in querying topics of interest in digital news library. To detect the caption from video sequence, we present algorithms based on fuzzy clustering neural networks. Since neural networks have the capabilities of learning and self-organizing and parallel computing mechanism, with the great increasing of digital images and video databases, neural networks based techniques become more efficient and popular tools for multimedia processing. Experimental results show that our caption detection scheme is effective and robust.

This work presents a novel approach to the segmentation of a textured image. We give a new validity function to check the validity of cluster number, it ensures the clustering results being fit for the real data structure by the aid of training of neural network. Then we synthesize traditional fuzzy clustering approaches and neural network to research the texture segmentation. The adaptive algorithm mainly includes three process: (1) feature extraction, extracting the texture features; (2) feature classification, using adaptively neural network to determine the clusters number; (3) fuzzy clustering, getting the results of classification and segmentation. Our experiments have proved the effectiveness of this method.

Partial distortion entropy maximization for online data clustering

In real-world environments, the human visual system perceives a wide range of luminance in a scene. However, the full range of tones in a high dynamic range (HDR) scene cannot be displayed on standard display devices due to their low dynamic range (LDR). Therefore, tone mapping is necessary to faithfully display a HDR scene on an LDR display device. Existing tone mapping methods have problems because details and contrast in a scene are not preserved faithfully, and they also distort the colors in a scene. Thus, we propose a tone mapping method for preserving the detail in an HDR scene using a weighted least squares filter, which preserves the global contrast in a scene by using a competitive learning neural network, before applying a tone reproduction operator to preserve the color without shifting the lightness. According to the Helmholtz–Kohlrausch effect, the perception of brightness depends on the lightness, chroma, and hue of a color. For example, the luminance of pixels with specific colors such as red and blue is low in an HDR scene. The proposed method corrects the lightness of pixels according to the color (i.e., lightness, chroma, and hue) of a tone-mapped image. Experimental results with several test sets of images demonstrated that the proposed tone mapping method with contrast preservation and lightness correction is more suitable for dynamic range compression than existing tone mapping methods, while it also preserves the color of a scene in an effective way.

Segmentation of images into textural homogeneous regions is a fundamental problem in an image understanding system. Most region-oriented segmentation approaches suffer from the problem of different thresholds selecting for different images. In this paper an adaptive image segmentation based on vector quantization is presented. It automatically segments images without preset thresholds. The approach contains a feature extraction module and a two-layer hierarchical clustering module, a vector quantizer (VQ) implemented by a competitive learning neural network in the first layer. A near-optimal competitive learning algorithm (NOLA) is employed to train the vector quantizer. NOLA combines the advantages of both Kohonen self- organizing feature map (KSFM) and K-means clustering algorithm. After the VQ is trained, the weights of the network and the number of input vectors clustered by each neuron form a 3- D topological feature map with separable hills aggregated by similar vectors. This overcomes the inability to visualize the geometric properties of data in a high-dimensional space for most other clustering algorithms. The second clustering algorithm operates in the feature map instead of the input set itself. Since the number of units in the feature map is much less than the number of feature vectors in the feature set, it is easy to check all peaks and find the `correct' number of clusters, also a key problem in current clustering techniques. In the experiments, we compare our algorithm with K-means clustering method on a variety of images. The results show that our algorithm achieves better performance.

Aiming at the problem of the coexistence of nonlinearity and uncertainty in the control systems, a novel control method which combines the double hidden layer fuzzy emotional recurrent neural network (DHLFERNN) and the recursive terminal sliding mode control (RTSMC) is proposed. Firstly, a novel double hidden layer fuzzy emotional recurrent neural network (DHLFERNN) is designed. The proposed DHLFERNN can be considered as a combination of a fuzzy neural network (FNN) and a double hidden layer recurrent neural network (DHLRNN) in the framework of brain emotional learning (BEL), which could make the controller obtain higher nonlinear approximation ability. Secondly, a recursive terminal sliding mode control (RTSMC) method based on the DHLFERNN is proposed. In this method, the nonlinear sliding-mode equivalent control term is approximated by the proposed DHLFERNN, which makes the controller possess a good nonlinear approximation ability when the nonlinear model cannot be obtained exactly. Finally, the stability of closed-loop system is proved by the Lyapunov method, and the adaptive law of each parameter in DHLFERNN is derived. The proposed method is verified on an inverted pendulum system, and the comparison with other control methods proves that the proposed method has faster convergence speed and higher control accuracy.

Provides an abstract of the presentation and a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings.

An interval-valued fuzzy cerebellar model neural network (IV-FCMNN) is proposed for the identification and control of uncertain systems. It is a more general model that uses the framework of a cerebellar model neural network (CMNN) and Atanassov intuitionistic fuzzy sets (AIFSs), so that the mathematical representation of a fuzzy event is more complete and the fuzzy neural network is more general. In some special cases, this neural network can be reduced to an interval-valued fuzzy neural network (IV-FNN), a fuzzy neural network (FNN), a fuzzy cerebellar model neural network (FCMNN) or a CMNN. Since the interval-type input data are used to realize this algorithm, the IV-FCMNN copes better with uncertainty and allows greater freedom of design. Therefore, the ability to learn, the approximation precision and the fuzzy semantic description of this network are much better than those of other models. In the proposed IV-FCMNN, a training algorithm that uses a gradient descent method is proposed to adjust the parameters and convergence is proved using the Lyapunov stability theorem. The variable learning rates are analyzed and the optimal learning rates are also determined. For demonstrating the effectiveness of the proposed IV-FCMNN, three types of applications, including multiple functions approximation, multi-dimensional classification and nonlinear dynamic system feedback control, are performed and the comparison with other models are also provided.

The performance assessment of hydraulic servo systems has attracted an increasing amount of attention in recent years. However, only a few studies have focused on practical approaches in this field. A performance assessment method based on radial basis function (RBF) neural network and Mahalanobis distance (MD) is proposed in this study; the method is quantized by the performance confidence value (CV). An observer model based on RBF neural network is designed to calculate the residual error between the actual and estimated outputs. The root mean square (RMS), peak value, and average absolute value are then extracted as the features of residual error, which serve as the coordinates of the feature points. Lastly, the MD between the most recent feature point and the constructed Mahalanobis space is calculated. The condition of the system is assessed by normalizing MD into a CV. The proposed method is proven to be effective by a simulation model in which leakage faults are injected. Experimental results show that the proposed method can assess the performance of hydraulic servo systems effectively.

A novel approach for fault detection in high voltage DC transmission systems using neural networks is presented. In the presented method, at first, Harmonics of voltage waveform in rectifier side are derived rapidly by using an adaptive linear neuron. Then, different types of faults including DC line fault, AC system fault and converter's faults are detected property using proposed criterion. In the under study voltage DC transmission systems system, rectifier and its controllers and required filters is modeled completely. A proposed criterion is tested on a high voltage DC system by computer simulation performed in MATLAB/Simulink environment. Simulation resulted demonstrates that the proposed approach can be used for online fault detection in high voltage DC systems.

The fuzzy logic and neural networks are combined in this paper, setting up the fuzzy neural network (FNN); meanwhile, the distinct differences and connections between the fuzzy logic and neural network are compared. Furthermore, the algorithm and structure of the FNN are introduced. In order to diagnose the faults of nuclear power plant, the FNN is applied to the nuclear power plant, and the intelligence fault diagnostic system of the nuclear power plant is built based on the FNN. The fault symptoms and the possibility of the inverted U-tube break accident of steam generator are discussed. In order to test the system’s validity, the inverted U-tube break accident of steam generator is used as an example and many simulation experiments are performed. The test result shows that the FNN can identify the fault.

This paper proposes a novel input-output clustering approach for structure identification of T-S fuzzy neural networks. This approach consists of two phases. Firstly, k-means clustering method is applied to the input data to provide the initial clusters of the input space. Secondly, check whether the sub-clustering is needed for each input cluster by considering the corresponding output variation and then apply the k-means method to further partition those input clusters needed sub-clustering. Applying the above process recursively leads to the structure identification of a T-S fuzzy neural network and then the parameter identification is completed by using the gradient learning algorithm. The experiments by applying the proposed method to several benchmark problems show better performance compared with many existing methods and then verify the effectiveness and usefulness of the proposed method.

Path planning is one of the key technologies in the research of mobile robots. Based on the research of fuzzy theory and neural network, a new algorithm is proposed, namely fuzzy neural network. The fuzzy neural network can be processed in parallel and self-learning like a neural network, and can also process fuzzy information like fuzzy theory and complete the fuzzy inference function. The fuzzy neural network is used to plan the path of the mobile robot, and the respective advantages of the fuzzy theory and the neural network are fully utilized to obtain the optimal path from the starting point to the target point. The simulation experiment was carried out under the condition that the environmental information is completely unknown and static. The results show that: The algorithm has high efficiency and fast convergence speed and effectively improves the intelligent level of the mobile robot.