Adaptive robust synchronization method is proposed for chaos synchronization of Lurie systems with time-varying delay. To weaken the restrictions on the change rate of time-varying delay in synchronization problems, adaptive estimations related to the derivative's upper bound of the time-varying delay are designed, so this upper bound can be unknown. The Lipschitz constant of the nonlinear link is also adaptively estimated, rather than being pre-calculated. Whole design is in the framework of robust control, and the synchronization can endure disturbance effectively. In addition, the synchronization of chaotic Lurie system with time-varying delay is realized as an example.
With the increasing role of computing devices, facilitating natural human computer interaction (HCI) will have a positive impact on their usage and acceptance as a whole. For long time, research on HCI has been restricted to techniques based on the use of keyboard, mouse, etc. Recently, this paradigm has changed. Techniques such as vision, sound, speech recognition allow for much richer form of interaction between the user and machine. The emphasis is to provide a natural form of interface for interaction. Gestures are one of the natural forms of interaction between humans. As gesture commands are found to be natural for humans, the development of gesture control systems for controlling devices have become a popular research topic in recent years. Researchers have proposed different gesture recognition systems which act as an interface for controlling the applications. One of the drawbacks of present gesture recognition systems is application dependence which makes it difficult to transfer one gesture control interface into different applications. This paper focuses on designing a vision-based hand gesture recognition system which is adaptive to different applications thus making the gesture recognition systems to be application adaptive. The designed system comprises different processing steps like detection, segmentation, tracking, recognition, etc. For making the system as application-adaptive, different quantitative and qualitative parameters have been taken into consideration. The quantitative parameters include gesture recognition rate, features extracted and root mean square error of the system while the qualitative parameters include intuitiveness, accuracy, stress/comfort, computational efficiency, user's tolerance, and real-time performance related to the proposed system. These parameters have a vital impact on the performance of the proposed application adaptive hand gesture recognition system.
Recently, applying control theory to regulate the intracellular mRNA level was introduced as a new direction for gene regulation. However, the high nonlinearity in the gene regulatory networks imposes significant challenges in control design. As a well understood benchmark example, the GAL regulatory network in S. cerevisiae was recently proposed as a test-bed system for validating theoretical control algorithms in cellular systems. A simple proportional feedback control approach was previously proposed for regulating the intracellular mRNA level in the GAL network, however, there were still limitations with its use to control the nonlinear GAL network. To improve the performance and effectiveness, this paper proposes an advanced nonlinear control strategy. The reduced mathematical model for the GAL network is reorganized into a nonlinear affine system. Then, a partial feedback linearization control approach was employed to regulate the concentration of a protein at a desired level. For validating the control approach in experimental studies, we choose Gal1p as a measurable output, instead of GAL1 mRNA used in the previous study. Simulation results demonstrate that this control approach can shorten the convergence time between states comparing with the proportional feedback control.
Many computer vision problems consist of making a suitable content description of images usually aiming to extract the relevant information content. In case of images representing paintings or artworks, the information extracted is rather subject-dependent, thus escaping any universal quantification. However, we proposed a measure of complexity of such kinds of oeuvres which is related to brain processing. The artistic complexity measures the brain inability to categorize complex nonsense forms represented in modern art, in a dynamic process of acquisition that most involves top-down mechanisms. Here, we compare the quantitative results of our analysis on a wide set of paintings of various artists to the cues extracted from a standard bottom-up approach based on visual saliency concept. In every painting inspection, the brain searches for more informative areas at different scales, then connecting them in an attempt to capture the full impact of information content. Artistic complexity is able to quantify information which might have been individually lost in the fruition of a human observer thus identifying the artistic hand. Visual saliency highlights the most salient areas of the paintings standing out from their neighbours and grabbing our attention. Nevertheless, we will show that a comparison on the ways the two algorithms act, may manifest some interesting links, finally indicating an interplay between bottom-up and top-down modalities.
A telemedicine system will provide sustainable, comprehensive, low-cost, fast, private, and convenient access to medical consultation and diagnosis for patients from remote locations. The telemedicine system addressed in this paper consists of a sensor jacket, which is worn by the patient for medical monitoring. The signals sensed through the jacket are processed and transmitted through a public telecommunication link, to a medical professional in a hospital at distance. The medical professional interacts with the patient through audio and video links, and simultaneously examines the data transmitted by the monitoring system. Medical assessment, diagnosis, and prescription are carried out on this basis. Sensing and signal processing are paramount to providing the patient data to the medical professional in an accurate and effective manner. This paper presents some relevant issues and techniques. Specific examples of electrocardiograms and respiratory signals are provided to illustrate the applicable signal conditioning approaches. Results are presented to demonstrate the feasibility and the effectiveness of these methods.
This paper focuses on a design of improved framework and analysis of existing framework which exploits certain algorithms for tracking online community in social network. Tracking of online community is an imperative task where the goal is to identify meaningful group structures in the dynamic social network and consider the problem of the evolution of groups of users in dynamic scenarios. Existing frameworks for tracking community in social network have some limitation which makes it less scalable and computationally inefficient. This novel framework facilitates scalable tracking communities over the time in social networks and offers efficient methods to deal with the problems which are offered in most of the existing frameworks.
When kernel methods are applied to detect the defection, there is a need to select the training samples, because kernel methods are based on the statistical learning theory. To extract the defects, the pre-image is calculated. In this paper, a sampling algorithm based on the alignment is designed to improve the calculation efficiency, where kernel alignment can measure the similarity between different kernel functions and matrices. A local linear algorithm is proposed to calculate the pre-image. When obtain the 0–1 difference image, an algorithm is designed to determine whether there are defects. An algorithm is designed to calculate the center coordinates and the areas of defects in the 0–1 image. Using this method, the accuracy of detection can be improved, because the method can remove the effect from recovery errors. When using the algorithms on a data set of printing products, the experiment results show that the detection results are more accurately than using the difference matrix.
A novel variational multiphase level set mathematical model is derived for image segmentation with two contributions. By virtue of eliminating the time-consuming re-initialization procedure and neglecting the property of the level set function during the evolution process, we in this paper present two strategies that may be taken as our contributions to solving these problems. Two scenarios are considered, namely, first, the distance regularization term which is defined by double-well potential function with two minimum points is introduced to our mathematical model for avoiding the re-initialization process. Second, by combining a Tikhonov-like regularization term which can guarantee the smoothness for the evolution curve over the previous method. Numerical simulation studies are presented to verify our new model via evaluating and comparing with existing algorithms.
A new watermarking approach based on affine Legendre moment invariants (ALMIs) and local characteristic regions (LCRs) which allows watermark detection and extraction under affine transformation attacks is presented in this paper. It is a non-blind watermarking scheme. Original image color image is converted into HSV color space and divided into four parts. LCR is constructed and a set of affine invariants are derived on LCRs based on Legendre moments for each part. These invariants can be used for estimating the affine transform coefficients on the LCRs. ALMIs are used for watermark embedding, detection and extraction as they provide synchronization and invariant feature which is necessary for a robust watermarking scheme. The proposed scheme shows resistance to geometric distortion, cropping, filtering, compression, and additive noise than the existing ALMI based scheme [Alghoniemy, M. and Tewfik, A. H. [2004] "Geometric invariance in image watermarking," IEEE Trans. Image Process13(2), 145–153] and affine geometric moment invariant (AGMI) based scheme [Seo, J. S. and Yoo, C. D. [2006] "Image watermarking based on invariant regions of scale-space representation," IEEE Trans. Signal Process. 54(4), 1537–1549].
This paper presents a fast palmprint verification system based on fractal coding. In the stage of registration, a sub-image from user's training palmprints is intentionally extracted and stored as his or her template. In the stage of verification, the step of region of interest extraction is not needed, the sample image is directly matched with the template based on fractal coding, which can reduce the whole response time. Whether the sample image and the template are from the same person or not is decided by their matching scores. Experimental evaluation results on two databases clearly demonstrate the effectiveness of the proposed approach.
In many fields of science, IT applications and business environments successfully evolved systems to receive vast amount of electronic data and information. Due to increasing electronic data and information, most recent researches have tried to find a solution to resolve the crisis of information overload. These solutions include a combination of techniques of data mining, machine learning, natural language processing and information retrieval, information extraction, and knowledge management. A great challenge is how to exploit those information and knowledge resources and turn them into useful knowledge available to concerned people. The value of knowledge increases when people can share and capitalize on it. Thus, approaches that can help researchers to benefit from existing hidden knowledge are needed. For this, tools that can analyze, extract and explore relevant and useful information with relations are required. So, the main contribution of this paper is to integrate the technology of XML with text analysis for introducing an efficient concept-based structure model, where this model can represent the text in a form that can be easily understood, shared, managed and mined. This paper describes an efficient object oriented text analysis (OOTA) approach by generating an object oriented model that transforms unstructured text to a specific structured form and stored in XML format. The experimental results show that this approach has a good promotion on results.
Particle swarm optimization (PSO) is one of the important evolutionary algorithms. However, the traditional PSO suffers from the premature convergence problem. In view of this, a new PSO, named mutation PSO (MPSO), is proposed in this paper. The proposed MPSO not only makes use of a mutation operator to update particles/individuals, which was originally designed for genetic algorithm (GA). But also a new weighted update rule is proposed for MPSO to produce the new swarm. Then we use the proposed MPSO to train multilayer perceptron (MLP) with two tasks: curve fitting and classification. In particular, the performance investigation is concentrated on scene classification. For a comparison purpose, MLPs trained using the error backpropagation (BP), traditional PSO and GA are also investigated. The advantages and disadvantages of these algorithms are also analyzed. Experimental results show that the proposed MPSO outperforms than other algorithms for the training of an MLP.
Breast cancer is the leading cause of death in women. Early detection and early treatment can significantly reduce the breast cancer mortality. Texture features are widely used in classification problems, i.e., mainly for diagnostic purposes where the region of interest is delineated manually. It has not yet been considered for sonoelastographic segmentation. This paper proposes a method of segmenting the sonoelastographic breast images with optimum number of features from 32 features extracted from three different extraction methods: Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Edge-Based Features. The image undergoes preprocessing by Sticks filter that improves the contrast and enhances the edges and emphasizes the tumor boundary. The features are extracted and then ranked according to the Sequential Forward Floating Selection (SFFS). The optimum number of ranked features is used for segmentation using k-means clustering. The segmented images are subjected to morphological processing that marks the tumor boundary. The overall accuracy is studied to investigate the effect of automated segmentation where the subset of first 10 ranked features provides an accuracy of 79%. The combined metric of overlap, over- and under-segmentation is 90%. The proposed work can also be considered for diagnostic purposes, along with the sonographic breast images.
Particle swarm optimization (PSO), a prevalent optimization algorithm, has been successfully applied to various fields of science and engineering. However, PSO still suffers from some problems such as premature convergence. To solve these problems, we propose a mutation PSO (MPSO) in this paper. Compared with the traditional PSO, there are two main improvements of the proposed MPSO. First, a new particle update rule is explored. The new rule updates a particle's position according to not only its best known position and the global best known position of the swarm, but also a number of other particles' best known positions. The second improvement is that a mutation operator is employed. Mutation operator is used to avoid premature convergence. The MPSO is utilized to train a multilayer perceptron (MLP). The MLP trained by MPSO is finally applied to two classification problems: Iris flower classification and scene classification. For comparison purposes, traditional PSO, genetic algorithm (GA), and back-propagation (BP) are also investigated. Experimental results demonstrate the superior performance of the proposed MPSO for MLP training.
In this paper, an efficient and low-cost cellphone-commandable mobile manipulation system is described. Aiming at house and elderly caring, this system can be easily commanded through common cellphone network to efficiently grasp objects in household environment, utilizing several low-cost off-the-shelf devices. Unlike the visual servo technology using high quality vision system with high cost, the household-service robot may not afford to such high quality vision servo system, and thus it is essential to use some of low-cost device. However, it is extremely challenging to have the said vision for precise localization, as well as motion control. To tackle this challenge, we developed a realtime vision system with which a reliable grasping algorithm combining machine vision, robotic kinematics and motor control technology is presented. After the target is captured by the arm camera, the arm camera keeps tracking the target while the arm keeps stretching until the end effector reaches the target. However, if the target is not captured by the arm camera, the arm will take a move to help the arm camera capture the target under the guidance of the head camera. This algorithm is implemented on two robot systems: the one with a fixed base and another with a mobile base. The results demonstrated the feasibility and efficiency of the algorithm and system we developed, and the study shown in this paper is of significance in developing a service robot in modern household environment.
This paper presents a comparative evaluation of two classification schemes that can be used to accurately diagnose the health of machines in the presence of sensor failure. In the developed approach, multiple sensors acquire vibration and sound signals from a machine and the signals are represented using the Wavelet Packet Transform (WPT). A “wrapper” feature selection procedure is used to reduce the size of the feature set without sacrificing the classification accuracy. The performance of a Radial Basis Function Network (RBFN) is compared with that of a Support Vector Machine (SVM) by simulating and monitoring machine and sensor faults in an industrial fish cutting machine. Initial results show an 85% reduction in feature set size for an RBFN and a 92.5% reduction in feature set size for a SVM.
Low earth orbit (LEO) satellite systems allow a broad range of services to be provided using small, lightweight, cellular-like portable telephones. Exploiting LEO satellites to support distress signals for aircrafts, ships and international travelers is explored in the current paper. A multi-service priority-oriented algorithm is proposed for handling voice, data and emergency signals over LEO satellites. The emergency signal is privileged with service priority so that rescue operation can be carried out as soon as possible. The priority mechanism includes channel reservation as well as joining a queue if no free channel is available as long as the request is roaming in the handover area. In addition, a simplified but efficient approach is suggested for locating the object of an imminent danger situation. As LEO satellites are non-geostationary, the visible period of each spot-beam is small. Consequently, a teletraffic model, that accommodates the mobility of spot-beams as well as the resulting handover rate, is developed in order to gauge the performance of the proposed algorithm. Numerical results for access denying and service-dropping rates are presented for nominal system parameters.
In intelligent vehicle system, it is significant to detect and identify road markings for vehicles to follow traffic regulation. This paper proposes a method to recognize direction markings on road surface, which is on the basis of detected lanes and uses Hu moments. First of all, the detection of lanes is based on horizontal luminance difference, which converts the RGB color image to the luminance image, calculates the horizontal luminance difference, obtains the candidate points of lanes' edge and uses least square method to fit the lanes. Secondly, with the detected lines as guide for the search of candidate marking, the paper extracts Hu moments of candidate marking, calculates its Mahalanobis distance to every marking type and classifies it to the type which has the minimal distance with the candidate marking. From the simulation results, the method to detect lanes is more effective and time-efficient than canny or sobel edge detection methods; the method to recognize direction marking is effective and has a high accuracy.
This work investigates the potential use of temperature modulation of MOS gas sensors combined with the Hilbert–Huang transform (HHT) as a feature extraction mechanism for MOS-based electronic noses. Five samples each of ethyl acetate, ethanol and isopropanol were prepared. The response of each of four sensors in an array was decomposed using empirical mode decomposition and the marginal Hilbert spectrum was computed. A set of 72 frequency components was extracted from marginal Hilbert spectrum response of each sensor in an array of four sensor to produce a 288 element fingerprint of each sample. The fingerprints were successfully clustered using PCA and classified using a SVM neutral network.
To enhance the effectiveness of learning genetics, we have developed a series of individual computer programs integrating interactivity with animated processes. It was noted that, although the content of the programs varied, the programs all contained a number of common features, including the ability to display text and images, present animated content, and interact with the user. These common features led us to the development of an innovative and unified framework of integrated functions for modeling and simulations. The framework, named "GeneAct" was developed to standardize and accelerate the development of the computer based genetics learning programs and was used as the application programming interface (API). The API allows the content to be imbued with rich text (text with multi-formats), static images, and animations; and it also allows the program to be interactive.
